HPC AI Agent Architect: Tool-Use & LLM Expert

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

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.