Research Scientist – Reinforcement Learning (RL)
$200k - $400k • New York City • FullTime
Posted 16d ago
Job Location
New York City
Tech Stack
Remote Work Policy
On-site
Employment Type
FullTime
Categories
AI Research Engineer
About the job
Percepta is transforming critical institutions with applied AI, embedding with industry-leading customers to drive AI transformation. We bring together forward-deployed expertise in engineering, product, and research, along with our in-house toolkit for rapidly deploying agentic workflows and strategic partnerships. As a Research Scientist - Reinforcement Learning, you will work at the intersection of RL research and real-world deployment, advancing decision-making capabilities for critical industries. You will collaborate closely with Embedded Product Managers and engineers to ensure our solutions transform how companies operate.
Responsibilities
- Identify real-world challenges tractable for RL-guided decision making.
- Develop RL methods for complex tasks in planning, decision-making, or optimization.
- Develop and maintain experimental infrastructure, including simulation environments, data pipelines, and training/evaluation frameworks.
- Conduct large-scale, in-the-wild evaluations that drive significant value.
- Partner with applied AI engineers to transition research into robust features for the Mosaic platform.
- Communicate research outcomes to both technical and non-technical stakeholders, explaining the impact and application of research.
Requirements
- MS/PhD in Computer Science, ML, or related field, or equivalent experience.
- Track record of effective RL work.
- Motivation by impact in critical industries (healthcare, supply chains, energy, finance).
- Understanding of rigorous RL experimentation.
- Enjoyment of extreme ownership.
- Belief that AI can drive transformative change in critical industries.
- High performance, large scale distributed systems experience.
- Large scale LLM training or RL training experience.
- Strong programming skills, especially in Python.
- Experience 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 (e.g., VeRL, ROLL, SkyRL, AReal, or RL libraries like CleanRL).
Benefits
- Competitive compensation
- Equity
- 401(k) matching
- Comprehensive health and family benefits
- Lunch every day