Research Scientist – Reinforcement Learning (RL)

The role

You will work at the intersection of RL research and real-world deployment. You will advance capabilities through research on decision-making for critical industries.

What you will do

• Identifying which real-world challenges are tractable for RL-guided decision making.
• Develop RL methods to perform complex tasks in domains like planning, decision-making, or optimization.
• Develop and maintain the experimental infrastructure that powers our research.
• Conduct in-the-wild evaluations at scale.
• Partner with applied AI engineers to transition research ideas into Mosaic platform features.
• Communicate research outcomes to technical and non-technical stakeholders.

Required qualifications

• MS/PhD in Computer Science, ML, or related field, or equivalent experience.
• A track record of effective RL work.
• Understand how to perform rigorous RL experimentation.
• Strong programming skills, especially in Python.

Nice to have

• High performance, large scale distributed systems.
• Large scale LLM training or RL training.
• Implementing LLM post-training algorithms.
• Experience with vLLM/SGLang, Ray, Kubernetes (or AWS EKS).
• Experience with distributed checkpointing, multi-node, multi-gpu training, custom KV-caching.
• Experience with asynchronous training and inference, either with VeRL, ROLL, SkyRL, AReal, or with RL libraries like CleanRL.

Benefits

• Competitive compensation
• Equity
• 401(k) matching
• Comprehensive health and family benefits
• Lunch every day

About the company

Percepta is a direct partnership with General Catalyst. Its mission is to transform critical institutions with applied AI.