Ai Agent & Tool-Use Engineer (Re2)

Barcelona Supercomputing Center; Barcelona; On-site; EUR 60,000 - 80,000; Full time

Benefits offered by this job

Restaurant tickets

Private health insurance

Relocation support

Flexible working hours

Job summary

Barcelona Supercomputing Center in Barcelona is seeking a talented AI Researcher to design and implement advanced language modeling techniques for high-performance computing environments. You will work on agentic workflows, model interactivity, and evaluation pipelines, collaborating with international experts across disciplines.

The role requires a degree in CS/Math, strong Python and PyTorch skills, experience with post-training of LLMs, and excellent English.

Qualifications

• Solid experience in fine-tuning and post-training of large language models.
• Experience with Agentic AI patterns such as ReAct or autonomous tool-use.
• Proficiency in Python and PyTorch.
• Hands-on experience with TRL, FastChat, NeMo-RL post-training frameworks.
• Excellent written and spoken English.

Responsibilities

• Implement and test agentic workflows including multi-step reasoning and tool-use capabilities under supervision.
• Develop and refine Function Calling interfaces and MCP connectors to enhance model interactivity.
• Execute post-training experiments using TRL, FastChat, and NeMo-RL to improve agentic performance.
• Build and maintain evaluation pipelines to measure reliability and safety of model-tool interactions.
• Collaborate with data team to curate high-quality instruction datasets for task-oriented dialogue.

Skills

Fine-tuning LLMs

Post-training LLMs

Agentic AI patterns (ReAct)

Python

PyTorch

Post-training frameworks TRL/FastChat/

English proficiency

Education

Degree in Computer Science/Mathematics or related

Job description

This position is at Barcelona Supercomputing Center The selection process will be entirely managed by Barcelona Supercomputing Center.

• Reference: ****** AII LM RE2 Job title: AI Agent particularly in deep learning, large language model development, instruction tuning, and agentic workflows, as well as related areas of Natural Language and Speech Processing.

The successful candidate will work in a highly sophisticated HPC environment, access state-of-the-art computational infrastructure, and collaborate with leading experts both locally and internationally.

The researcher will be responsible for designing and implementing innovative techniques for language modeling, evaluation and system adaptation tailored to high-performance computing systems.

Key Duties

• Implement and test agentic workflows including multi-step reasoning and tool-use capabilities under the supervision of the senior architect.
• Develop and refine Function Calling interfaces and connectors using the Model Context Protocol (MCP) to enhance model interactivity.
• Execute post-training experiments using TRL, FastChat, and NeMo-RL to improve the agentic performance of small and large models.
• Build and maintain evaluation pipelines specifically designed to measure the reliability and safety of model-tool interactions.
• Collaborate with the data team to curate high-quality instruction datasets for task-oriented dialogue and function execution.

Requirements

• Education Degree in Computer Science, Mathematics or related.

Essential Knowledge and Professional Experience

• Solid experience in Fine-tuning and Post-training of Large Language Models.
• Practical experience with Agentic AI patterns such as ReAct or autonomous tool-use.
• Proficiency in Python and Deep Learning libraries like PyTorch.
• Hands-on experience with modern post-training frameworks including TRL, FastChat, or NeMo-RL.
• Excellent level of written and spoken English.

Additional Knowledge and Professional Experience

• Familiarity with Model Context Protocol (MCP) and API integration for LLMs.
• Knowledge of advanced preference alignment methods like DPO, GSPO, or CISPO.
• Experience in developing benchmarking tools for function calling and reasoning.

Competences

• Strong technical execution skills with a focus on reproducibility and clean code.
• Ability to work effectively in a team-oriented research environment.
• Proactive problem-solving mindset when dealing with complex system integrations.
• Detail-oriented approach to evaluating model reliability and edge cases.

Conditions

The position will be located at BSC within the Directors Department We offer a full-time contract (35h/week), a good working environment, a highly stimulating environment with state-of-the-art infrastructure, flexible working hours, extensive training plan, restaurant tickets, private health insurance, support to the relocation procedures Duration: Open-ended contract due to technical and scientific activities linked to the project and budget duration Holidays: 22 days of holidays + 6 personal days + 24th and 31st of December per our collective agreement Salary: we offer a competitive salary commensurate with the qualifications and experience of the candidate and according to the cost of living in Barcelona Starting date: ASAP.

Development of the recruitment process

The selection will be carried out through a competitive examination system ("Concurso-Oposición").

The recruitment process consists of two phases: Curriculum Analysis: Evaluation of previous experience and/or scientific history, degree, training, and other professional information relevant to the position.

• 40 points Interview phase: The highest-rated candidates at the curriculum level will be invited to the interview phase, conducted by the corresponding department and Human Resources.
• 60 points.

A minimum of 30 points out of 60 must be obtained to be eligible for the position.

The recruitment panel will be composed of at least three people, ensuring at least 25% representation of women.

In accordance with OTM-R principles, a gender-balanced recruitment panel is formed for each vacancy at the beginning of the process.

After reviewing the content of the applications, the panel will begin the interviews, with at least one technical and one administrative interview.

At a minimum, a personality questionnaire as well as a technical exercise will be conducted during the process.

The panel will make a final decision, and all individuals who participated in the interview phase will receive feedback with details on the acceptance or rejection of their profile.

At BSC, we seek continuous improvement in our recruitment processes.

Deadline The vacancy will remain open until a suitable candidate has been hired.

Applications will be regularly reviewed and potential candidates will be contacted.

OTM-R principles for selection processes BSC-CNS is committed to the principles of the Code of Conduct for the Recruitment of Researchers of the European Commission and the Open, Transparent and Merit-based Recruitment principles (OTM-R).

This is applied for any potential candidate in all our processes, for example by creating gender-balanced recruitment panels and recognizing career breaks etc.

BSC-CNS is an equal opportunity employer committed to diversity and inclusion.

We are pleased to consider all qualified applicants for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability or any other basis protected by applicable state or local law.