hr Archives - rinf.tech https://www.rinf.tech/tag/hr/ Sun, 16 Nov 2025 16:40:53 +0000 en-US hourly 1 https://www.rinf.tech/wp-content/uploads/2020/05/favicon-150x150.png hr Archives - rinf.tech https://www.rinf.tech/tag/hr/ 32 32 AI-Driven Solution for Talent Acquisition: a White Paper  https://www.rinf.tech/ai-driven-solution-for-talent-acquisition-a-white-paper/ Tue, 28 May 2024 12:02:04 +0000 https://www.rinf.tech/?p=27732 This paper presents an innovative AI-enhanced SaaS solution designed to tackle the complex challenges of resume classification, job description matching, and the creation of customized resumes and cover letters. 

The post AI-Driven Solution for Talent Acquisition: a White Paper  appeared first on rinf.tech.

]]>

AI-Driven Solution for Talent Acquisition: a White Paper 

Contents

Introduction

In the rapidly evolving landscape of Talent Management (TM), the integration of Artificial Intelligence (AI) into Software as a Service (SaaS) platforms is set to revolutionize talent acquisition processes. This paper presents an innovative AI-enhanced SaaS solution designed to tackle the complex challenges of resume classification, job description matching, and the creation of customized resumes and cover letters. 

Project Hypothesis

Our AI Team has been tasked with developing a comprehensive solution that leverages the capabilities of Large Language Models (LLMs) to streamline HR processes. The goal is to accurately classify and match resumes to job descriptions, score resumes, generate and update resumes, cover letters, and job descriptions, and provide actionable recommendations. 

Problem Framing

The industry-wide issue that needs to be addressed is the lack of a standardized frame of reference for benchmarks and comparisons, scoring, and ranking of what a candidate’s CV offers and what a job description demands. We propose tackling this problem using a “taxonomy anchor” as the benchmark scale to measure the “suitability” of a CV or set of CVs for a given job description through categorization.

Proposed Solution

Our team proposes creating a modularized solution for parsing CVs and Job Descriptions (JDs), matching CVs against a given JD or through the summarization and reasoning of an LLM model fine-tuned on ESCO/ISCO/US SOC standards. The solution also aims to propose a JD for a given CV and score the “fit” of a CV. 

The proposed solution is designed to be modular, allowing for the integration of various components as needed. This includes a parser for extracting relevant information from CVs and JDs, a matcher for aligning CVs with appropriate JDs, and a scoring system for evaluating the fit of a CV for a given JD. The solution also includes a generator for creating and updating CVs, cover letters, and JDs based on the extracted information and the results of the matching and scoring processes. 

The key innovation of our solution lies in its use of LLMs, which have been fine-tuned on ESCO/ISCO/US SOC standards. These models can understand and reason about the content of CVs and JDs, allowing them to perform tasks such as summarization and matching with high accuracy. Furthermore, by grounding our solution in these occupational standards, we ensure that our analysis is always tied to a common frame of reference, allowing for meaningful comparisons and evaluations. 

The goal is to facilitate stepwise and progressive improvement iterations of the architecture, ensuring it excels in various phases of the workflow, including CV data ingestion and parsing, preprocessing, and the application of specialized LLM models tailored for embeddings (retriever) and Q&A functionalities (generator).  

Essentially, our solution focuses on the following:  

SaaS-based LLM solution for talent acquisition

Given the large variety of CV content, we prefer to employ a strategy for parsing CV’s so that we can extract content that can be further classified and can allow to associate the subsequent paragraphs in a detected section with the header of that section, which down the road simplifies the processing of the type of the extracted CV content.  

Model Training Pipeline – Framework 

Large Language Models (LLMs) represent a type of artificial intelligence that undergoes training on an extensive amount of web data and various online resources. This training enables them to produce responses to language-based inquiries that closely resemble human expression. Despite the impressive achievements already demonstrated by commercial and versatile LLMs such as ChatGPT, Gemini, and Claude, the prospective evolution of LLMs is trending towards models that are more focused on particular domains, possessing compactness and enhanced efficiency.  

In our given use case, the embedding models and the LLM models can greatly improve their accuracy and text generation relevance if both can be made aware of the ESCO/ISCO/US SOC standards and always reason within the boundaries of the associated Occupational codes for every information they’re asked to summarize or parse. Furthermore, models can be trained on domain-specific corpus such that a very high accuracy is obtained when analyzing a job description and a CV that are specific to the medical, legal or IT domains when the data is routed to the domain fine-tuned model.  

We propose a model training framework that builds upon the utilization of pretrained, in-domain Large Language Models. In-domain LLM’s present limited access to openly available checkpoints and the presence of exceedingly large models – like the 1.7 trillion parameters of GPT-4. However, the landscape of LLM research has evolved with a notable shift towards fully open-source LLM checkpoints, featuring commercially viable sizes ranging from 3 to 13 billion parameters.  

These open source LLMs have undergone pre-training with trillions of tokens and strike a great balance between size and functionality, rendering them exceptionally suitable for tasks demanding specialized or niche language comprehension.  

Within the proposed framework, our primary focus lies in constructing systems by customizing publicly available LLM checkpoints with domain-specific data. To achieve this objective, we emphasize the utilization of innovative Parameter Efficient Fine Tuning (PEFT) techniques like LORA and Quantization, which strike a balance between performance and computational expenditure.  

The proposed framework takes the approach of in-context fine-tuning for pre-trained LLMs using domain-specific datasets. This strategic step capitalizes on the inherent potential of the pre-existing model, thereby refining its contextual comprehension in alignment with the specific requirements of many organizations.  

As language modeling techniques have evolved, we have seen an increasing effectiveness in retrieval augmented generation (RAG), where the generator model is provided with relevant context documents from a context database. Documents are fetched with a retriever model which embeds them into a semantic space where they can be matched to queries at inference time.  

‍Despite the effectiveness of RAG, the generator and retrieval systems have evolved in separate stacks and are served at inference time together with multiple API calls. We not only perceive the necessity of multiple API calls as an issue but also advocate for a unified training approach for these systems, leading to their integration into a singular API that seamlessly incorporates both the generative and retrieval functionalities.  

Are you a seasoned AI engineer looking to join our core AI Team and work on state-of-the-art PoC and custom projects?

Check this out!

Review of Existing Approaches

While there exist numerous attempts at SaaS or locally deployed solutions that tackle the HR AI domain issues (skill extraction, general CV parsing, etc), there is no commercially available solution that uses occupational codes as a frame of reference to parse and analyze CVs and Job Descriptions and ensure the analysis is always grounded in a common denominator for both. 

Existing approaches to the problem of resume classification and job description matching typically rely on rule-based or machine learning algorithms. These methods, while effective in certain contexts, have significant limitations. Rule-based algorithms, for instance, are often brittle and unable to handle the complexity and variability of real-world data. Machine learning algorithms, on the other hand, require large amounts of labeled data and can struggle with tasks that require a deep understanding of the content of CVs and JDs. 

Our review of the existing literature and commercial solutions reveals a gap in the market for a solution that leverages the power of LLMs and occupational standards to address the challenges of resume classification and job description matching. Our proposed solution aims to fill this gap by offering a versatile and effective tool for talent acquisition. 

The following sections explain the main existing approaches and contextualize our approach. 

Supervised Approaches  

Supervised learning has conventionally been the dominant paradigm for occupation extraction and standardization. Typically, the extraction task is framed as a multiclass classification problem. Studies such as [3, 2, 4, 6] have evaluated the merits of SVMs and convolutional neural networks using English job titles labeled with ISCO codes. In a different vein, [20] employed an ensemble of five machine learning algorithms for classifying Greek job postings into ISCO categories. Other researchers like [1] have applied Naive Bayes and Bayesian Multinomial techniques for the prediction of KldB2021 codes using German survey data. Furthermore, investigations such as [18] and [17] have assessed the efficacy of a variety of supervised algorithms for classifying into American SOC codes. However, supervised methods often grapple with limitations tied to dataset size, language specificity, and taxonomy constraints.   

Our approach, by contrast, offers a versatile framework, adept at handling multiple languages and taxonomies through a cohesive pipeline.   

Unsupervised Approaches  

Initial endeavors in the realm of occupation and skill extraction leaned on techniques like rule-based labeling [14], keyword-driven searches [15], and topic modeling [10]. An intriguing observation from [22] highlighted that CASCOT, a rule-based approach, could sometimes surpass machine learning counterparts in specific evaluations. However, as the CV and Job Descriptions get more elaborate semantically, the performance of such systems still falls short when juxtaposed with the capacity of removing semantic noise via summarization of a fine-tuned LLM.  

Transformer-based LLMs   

To the best of our knowledge there is no commercial offering harnessing the capabilities of state-of-the-art GPT-style decoder-only models for occupation coding. While there exist some parallels in the HR AI domain, such as skill extraction, the focus has primarily been on BERT-like (encoder-only) architectures [7, 16]. For instance, [21] limited their scope to fine-tuning classification layers for skill categorization. Meanwhile, works like [5, 23] leveraged LLM embeddings as alternatives to traditional word2vec embeddings, albeit with the LLM playing a somewhat peripheral role in their Named Entity Recognition (NER) frameworks. Predominantly, prior endeavors have concentrated on tapping into LLMs for Natural Language Understanding (NLU) while our proposed approach covers new grounds by exploring the generative prowess (NLG) of LLMs specifically for OES.  

Ethical Considerations and Implications of the AI-Driven Solution for Talent Acquisition

The proposed AI-driven solution for talent acquisition, as described in this whitepaper, presents several ethical considerations and implications, particularly from a Bias and Fairness perspective: 

  • Bias and Fairness: The solution leverages Large Language Models (LLMs) that have been fine-tuned on ESCO/ISCO/US SOC standards. These standards provide a common frame of reference for analyzing CVs and Job Descriptions (JDs), which helps ensure that all candidates are evaluated based on the same criteria. This approach can help mitigate biases that might arise from subjective interpretations of CVs and JDs. Furthermore, the use of domain-specific models for different fields like medical, legal, or IT ensures that the evaluation is tailored to the specific requirements and terminologies of each domain, which can further enhance fairness. 
  • Transparency and Explainability: The modular design of the solution, with separate components for parsing, matching, scoring, and generating CVs and JDs, can potentially make it easier to explain how the system works and how it arrives at its decisions. This transparency is crucial for candidates to understand and trust the system. 
  • Privacy and Data Security: The solution involves processing sensitive personal data contained in CVs. It’s therefore essential to have robust data security measures in place and to use the data only for the intended purpose of matching candidates to job descriptions. Candidates should be informed about how their data will be used and stored, and their consent should be obtained. 

 

Our solution for talent acquisition has been designed with careful consideration of ethical issues related to bias, fairness, transparency, and data privacy. However, given the importance and criticality of this topic,  we continuously monitor and evaluate the system to ensure that these ethical standards are maintained in practice. 

Conclusion

Our solution stands out by offering a versatile framework that adeptly handles multiple languages and taxonomies, effectively addressing the limitations of supervised methods tied to dataset size, language specificity, and taxonomy constraints. Our model excels by leveraging the generative prowess of Large Language Models for occupation coding, offering an innovative edge over existing supervised and unsupervised methods. 

Future Work

Looking forward, our team is committed to continuous refinement of the LLM models to enhance domain-specific accuracy and task-oriented capabilities. We believe that our approach not only surpasses the capabilities of rule-based and machine learning algorithms but also marks a significant advancement by employing state-of-the-art LLMs in a way that previous efforts have not, particularly in the nuanced domain of occupation standardization and skill extraction. 

List of References 

[1] Bethmann, A., Schierholz, M., Wenzig, K., Zielonka, M.: Automatic coding of occupations using machine learning algorithms for occupation coding in several Ggerman panel surveys. In: Beyond traditional survey taking. Adapting to a changing world. Proceedings of Statistics Canada Symposium (2014)  

[2] Boselli, R., Cesarini, M., Marrara, S., Mercorio, F., Mezzanzanica, M., Pasi, G., Viviani, M.: Wolmis: A labor market intelligence system for classifying web job vacancies. Journal of intelligent information systems 51, 477–502 (2018)  

[3] Boselli, R., Cesarini, M., Mercorio, F., Mezzanzanica, M.: Using machine learning for labour market intelligence. In: Altun, Y., Das, K., Mielik¨ainen, T., Malerba, D., Stefanowski, J., Read, J., ˇZitnik, M., Ceci, M., Dˇzeroski, S. (eds.) Machine Learning and Knowledge Discovery in Databases. pp. 330–342. Springer International Publishing, Cham (2017)  

 [4] Boselli, R., Cesarini, M., Mercorio, F., Mezzanzanica, M.: Classifying on-line job advertisements through machine learning. Future Generation Computer Systems 86, 319–328 (2018)  

[5] Chernova, M.: Occupational skills extraction with FinBERT. Master’s thesis (2020)    

[6] Colombo, E., Mercorio, F., Mezzanzanica, M.: Ai meets labor market: Exploring the link between automation and skills. Information Economics and Policy 47, 27–37 (2019)  

[7] Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)  

[10] Gurcan, F., Cagiltay, N.E.: Big data software engineering: Analysis of knowledge domains and skill sets using lda-based topic modeling. IEEE access 7, 82541–82552 (2019)  

[14] Jones, R., Elias, P.: Cascot: Computer-assisted structured coding tool. Institute for Employment Research, Coventry, University of Warwick (2023). <https://warwick.ac.uk/fac/soc/ier/research-tools>  

[15] Kouretsis, A., Bampouris, A., Morfiris, P., Papageorgiou, K.: Labourr: classify multilingual labour market free-text to standardized hierarchical occupations (2020). <https://cran.r-project.org/web/packages/labourR/index.html>

 [16] Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., Stoyanov, V.: Roberta: A robustly optimized bert pretraining approach.  arXiv preprint arXiv:1907.11692 (2019)  

[17] Mukherjee, S., Widmark, D., DiMascio, V., Oates, T.: Determining standard occupational classification codes from job descriptions in immigration petitions. In: 2021 International Conference on Data Mining Workshops (ICDMW). pp. 647–652. IEEE (2021)  

[18] Russ, D.E., Ho, K.Y., Colt, J.S., Armenti, K.R., Baris, D., Chow, W.H.,Davis, F., Johnson, A., Purdue, M.P., Karagas, M.R., et al.: Computer based coding of free-text job descriptions to efficiently identify occupations in epidemiological studies. Occupational and environmental medicine 73(6), 417–424 (2016)  

[20] Varelas, G., Lagios, D., Ntouroukis, S., Zervas, P., Parsons, K., Tzimas, G.: Employing natural language processing techniques for online job vacancies classification. In: IFIP International Conference on Artificial Intelligence Applications and Innovations. pp. 333–344. Springer (2022)  

[21] Vermeer, N., Provatorova, V., Graus, D., Rajapakse, T., Mesbah, S.: Using robbert and extreme multi-label classification to extract implicit and explicit skills from dutchDutch job descriptions (2020)  

[22] Wan, W., Ge, C.B., Friesen, M.C., Locke, S.J., Russ, D.E., Burstyn, I., Baker, C.J., Adisesh, A., Lan, Q., Rothman, N., et al.: Automated coding of job descriptions from a general population study: overview of existing tools, their application and comparison. Annals of Work Exposures and Health 67(5), 663–672 (2023)  

[23] Zhang, M., Jensen, K.N., Plank, B.: Kompetencer: Fine-grained skill classification in danishDanish job postings via distant supervision and transfer learning. arXiv preprint arXiv:2205.01381 (2022)  

Related Articles

Looking for a technology partner?

Let’s talk.

The post AI-Driven Solution for Talent Acquisition: a White Paper  appeared first on rinf.tech.

]]> A #PeopleOfManyTalents Story https://www.rinf.tech/a-peopleofmanytalents-story/ Fri, 17 Jul 2020 12:36:53 +0000 https://www.rinftech.com/?p=6392 A #PeopleOfManyTalents Story rinf.tech is an independent technology company, ready to be the reliable partner for businesses and organizations aiming to architect the future within their industry and outside of it. A people of many talents’ story worth telling. Mihaela has been working at rinf.tech for over 2 years as a Talent Acquisition Specialist, carrying her work with great passion and being […]

The post A #PeopleOfManyTalents Story appeared first on rinf.tech.

]]>

A #PeopleOfManyTalents Story

rinf.tech is an independent technology company, ready to be the reliable partner for businesses and organizations aiming to architect the future within their industry and outside of it.

A people of many talents’ story worth telling.

Mihaela has been working at rinf.tech for over 2 years as a Talent Acquisition Specialist, carrying her work with great passion and being a resourceful colleague for us “non tech people” in a tech company.

One day, we have learned that she was about to leave her position as a recruiter, to join a technical team for one of our projects as a Software Developer.

How did you start your job in Talent Acquisition?

I started working in TA in August 2017 when I finished my master’s degree in ‘Organizational Psychology and Human Resources management’. I had about two years of experience in the field of recruitment and I was working in a recruitment agency at that time, but I was looking for a more flexible work environment.

 

What motivated you and kept you going?

The field of recruitment seemed to me extremely interesting and important in view of the fact that it manages to make a connection between a person looking for a job and an employer who needs the knowledge and skills of that person.

It is impressive to see how both sides succeed to achieve their goals and develop as a result of their collaboration.

What led you to make this change change?

The desire to make the change to programming began to appear from the first interviews I had with those in this field.

I was lucky enough to meet people very passionate about software development who also had the patience to explain many of the concepts that later led me to a training.

As I deepened my knowledge of programming, I realized that I liked it more and more. The hours spent in this regard passed very quickly.

There are two aspects that I like mainly in programming:

  1. The satisfaction that solving a difficult problem gives you
  2. The fact that the work done for the development of different applications can be useful for many people.

 

How you managed the transition and the impact with the new role?

The transition was easy for me because I am lucky to be part of a very good team from which I receive all the support I need now at the beginning.

Also, the flexible environment at RINF TECH and the professional opportunities I had here helped me a lot to have an easy transition, especially in this period when we could only have online interactions.

We want to thank Mihaela for her collaboration, express all our admiration and wish her the best of luck for her new role!

 

Looking for a technology partner?

Let’s talk.

The post A #PeopleOfManyTalents Story appeared first on rinf.tech.

]]> On developers’ happiness (and professional success). How to pick the right project for you https://www.rinf.tech/on-developers-happiness-and-professional-success-how-to-pick-the-right-project-for-you/ Mon, 13 Apr 2020 14:54:38 +0000 https://www.rinftech.com/?p=5828 On developers’ happiness (and professional success). How to pick the right project for you What aspects should you consider while choosing your new IT job? The Software Development industry, with its complexity, variety, and ramifications, has its challenges as far as regards the management of the human resources. The technologies employed evolve quickly and require […]

The post On developers’ happiness (and professional success). How to pick the right project for you appeared first on rinf.tech.

]]>

On developers' happiness (and professional success). How to pick the right project for you

What aspects should you consider while choosing your new IT job?

The Software Development industry, with its complexity, variety, and ramifications, has its challenges as far as regards the management of the human resources.

The technologies employed evolve quickly and require a constant reorganization of people and procedures.

The expertise must be kept fresh and up to date, as the tools to get the job done (primarily programming languages) change at a very fast pace, some tools fall into disuse, other ones replace them.

For a Technology company, it is necessary to change fast as well, and get accustomed to new ways of working. Thriving rhymes with flexibility and agility.

The right people in the right place

First, it is very important to develop an in-depth understanding of the terrain: what is the project about? What is our partner about?

Let me point out a banality, the success of a project does not only depend on filling the requested technologies with qualified resources – “end of the story”.

That is, for sure, a very good starting point, but excellent work is more like a football match, and a lot of us have seen teams with very skilled players performing badly during the game due to a lack of mentality, of synergy within the team.

The same way, the work of building a great tech product will come much easier if some efforts are put in finding good cultural matches between the team and the candidate.

Do you prefer a fixed working schedule, or you like to keep it more flexible?

Are you comfortable with working remote, and work with people who work remote on regular bases?

Which part of your career path are you walking today? Maybe you want to strengthen your knowledge on some common technologies and procedures, maybe it is time for you to explore with highly pioneering\experimental projects.

How do you get ready for a new project?

Technical skills match – Work with the tools you love to use and the ones you want to master, to value your knowledge today, and plant a seed to keep you growing as a professional.

Cultural match – How does your ideal working environment look like? We are building solutions for multiple partners. Shared values and culture make great collaborations!

Your professional journey – Your career path should follow the flow of your constantly renewing interests. Internal mobility programs to meet your curiosity and professional and personal goals. Pick the project that suits you!

Support at every step The company’s transparency and proactive participation build trust, confidence, and sustain long-term success.

Communicate and prepare – how do we handle the recruitment process, step by step?

  1. Discovery meeting – is a 30 to 60 minutes long call with one of our Talent Acquisition team members, to assess the candidate’s motivations and preferences in relation to their career journey.
  2. Tech review meeting – with a technical manager, the candidate will discuss about how his or her technical skills can be applied to the specific project.
  3. Offering meeting – a really important discussion. We have found a synergy in terms of professional and cultural sides, it’s time to address the commercial/legal details and kick off our collaboration!
  4. Feedback – We take care of sharing with the candidates our considerations on the work we have done together. We consider this to be a crucial part of the journey, a big source of value through which we and the people who get in touch with us can grow, whatever the outcome of the interviewing process is. You can read more about RINF TECH’s feedback culture here.

 

Looking for a technology partner?

Let’s talk.

The post On developers’ happiness (and professional success). How to pick the right project for you appeared first on rinf.tech.

]]>