Research Engineer, Post-training

The role

You will define post-training recipes for AI models and build post-training data pipelines. You will develop agentic systems and work with scientists and robotics engineers to bring reasoning capabilities into live experimental loops.

What you will do

• Define post-training recipes for AI models
• Build and own post-training data pipelines integrating internal and public data
• Create evaluations for model improvement in scientific protocols and assay development
• Develop agentic systems with context management and custom tool calls
• Work with scientists, robotics engineers, and operation teams to bring reasoning capabilities into live experimental loops
• Shape the engineering culture and technical direction of a new machine learning team

Required qualifications

• Practical experience building AI-driven workflows into the real world
• Strong problem solving skills for debugging complex systems
• A clear grasp of probability, statistics, and ML fundamentals
• Ability to own the post-training stack end-to-end including data pipelines, harnesses, RL environments, and agentic evaluations
• Proficiency in Python
• Familiarity with at least one deep learning framework (e.g., PyTorch, JAX)

Nice to have

• Experience with LLMs
• Experience with post-training
• Experience with reinforcement learning
• Experience with agentic systems

About the company

Medra is building Physical AI Scientists, which are robotic systems that work with biopharma partners to enable scientific breakthroughs. The company recently raised a $52M Series A and is opening one of the largest autonomous labs in the US.