Reinforcement Learning Scientist for Foundation Models

Institute of Foundation Models; Sunnyvale (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

Institute of Foundation Models in Sunnyvale, CA, seeks a Research Scientist in our Reinforcement Learning team to shape scientific and technical directions for emergent capabilities in foundation models. You will prototype novel RL approaches, contribute to large-scale training infrastructure, and produce replicable code for public release.

You will build a productive research portfolio through internal and external collaborations, publish results, and present at conferences, while advancing our

Qualifications

• 3+ years of hands-on experience with reinforcement learning.
• Demonstrated ability to independently identify limitations of current practice and formulate/ enact solution strategies.
• Proactive mindset with ability to identify impactful research questions and execute with minimal supervision.
• Strong Python development skills with focus on research-grade code and scalable data pipelines.
• Experience applying novel RL algorithms to practical applications.
• Strong publication record in AI/RL venues or open-source contributions.

Responsibilities

• Develop novel research toward massive-scale self-play for foundation model training and agentic tasks.
• Initiate and pursue novel RL algorithmic approaches to drive emergent capabilities in Foundation Models.
• Full-stack engineering from data curation, model architecture to production-ready code.
• Contribute to technical reports and research publications.
• Represent the institute at conferences and open-source communities.
• Contribute to large-scale RL training and inference frameworks.
• Facilitate internal and external collaboration.

Skills

Reinforcement learning

Python

Research

Communication

Open-source contribution

Education

MSc/MEng or PhD in Machine Learning/CS

Tools

PyTorch

JAX

Job description

Institute of Foundation Models in Sunnyvale, CA, seeks a Research Scientist in our Reinforcement Learning team to shape scientific and technical directions for emergent capabilities in foundation models. You will prototype novel RL approaches, contribute to large-scale training infrastructure, and produce replicable code for public release.

You will build a productive research portfolio through internal and external collaborations, publish results, and present at conferences, while advancing our