Research Engineer/Scientist (Reinforcement Learning) at Percepta

Setup: Remote
Location: New York, New York
Type: Full-time
Posted: Jan 22, 2026

Description

Percepta is seeking a Research Engineer/Scientist specializing in Reinforcement Learning. This role involves advancing cutting-edge capabilities in decision-making for critical industries such as healthcare, manufacturing, energy, and finance. The individual will develop and implement RL methods, conduct extensive experiments, and translate research findings into practical applications using the Mosaic platform. Collaboration with embedded product managers and engineers is essential to ensure impactful deployments.

Required Skills

Reinforcement Learning
decision-making
planning
optimization
experimental infrastructure
simulation environments
data pipelines
training and evaluation frameworks
large-scale distributed systems
LLM training
programming skills
Python

Additional Information

Required Previous Experiences: effective RL work
Preferred Qualifications: 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.
Have a track record of effective RL work.
Are motivated by impact in critical industries including healthcare, supply chains, energy, and finance.
Understand how to perform rigorous RL experimentation.
Enjoy extreme ownership.
Believe that AI can drive transformative change in critical industries.