Research Engineer, Conversational AI & LLMs

Permut; Barcelona; On-site; EUR 60,000 - 100,000; Full time

Job summary

Permut is seeking a Research Engineer to develop the intelligence behind its next generation of AI agents. You will shape how agents understand intent, leverage brand knowledge, and execute actions, balancing model adaptation with data curation and rigorous evaluation.

You’ll work on experiments that translate to production, establish research foundations, and measure progress with robust benchmarks. Collaboration with engineers and a focus on scalable, efficient AI systems drive this role.

Qualifications

• 3+ years of experience in AI or machine learning.
• Strong Python skills with PyTorch and the Hugging Face ecosystem.
• Hands-on LLM experience including fine-tuning and dataset preparation.
• Strong experimental judgment to establish baselines and assess improvements.
• Experience improving data quality: sampling, labeling, coverage, leakage prevention.
• Production awareness: latency, cost, reliability, monitoring.
• Autonomy and clear communication to ship research results.

Responsibilities

• Adapt, fine-tune and improve models for conversational tasks including product discovery, customer support and tool use.
• Build high-quality datasets from conversations, brand knowledge, agent actions and human feedback.
• Design benchmarks that measure factual accuracy, task completion, tool execution and conversation quality.
• Investigate failures across prompting, retrieval, context management and model behaviour, then design experiments to address them.
• Explore post-training approaches and feedback loops that improve agent performance over time.
• Work closely with engineering to deploy successful experiments and measure their impact on quality, latency, cost and reliability.

Skills

AI/ML experience

Python

LLM experience

Experimentation

Data quality

Production awareness

Communication

Tools

PyTorch

Hugging Face

Job description

Permut is seeking a Research Engineer to develop the intelligence behind its next generation of AI agents. You will shape how agents understand intent, leverage brand knowledge, and execute actions, balancing model adaptation with data curation and rigorous evaluation.

You’ll work on experiments that translate to production, establish research foundations, and measure progress with robust benchmarks. Collaboration with engineers and a focus on scalable, efficient AI systems drive this role.