RL Research Scientist — Foundations & Emergent AI

Ifm Us; Sunnyvale (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

The Institute of Foundation Models is seeking a Research Scientist to advance reinforcement learning methods for foundation models. You will prototype novel learning-from-experience approaches, contribute to large-scale training systems, and produce replicable, public code with collaborators.

You will build a productive research portfolio, publish in top venues, and engage with the open-source community while representing the lab at major conferences.

Qualifications

• 3+ years of hands-on reinforcement learning experience.
• Ability to identify limitations and propose improvements with minimal supervision.
• Strong Python development skills for research-grade code and scalable pipelines.

Responsibilities

• Develop novel RL methods for emergent capabilities in foundation models.
• Prototype and adapt learning-from-experience approaches for large-scale RL training.
• Contribute to scalable training infrastructure and maintainable codebases.
• Publish technical reports and papers; present at venues.
• Engage with open-source communities and external collaborations.
• Represent the institute at conferences and events.

Skills

Reinforcement learning

Python development

Open-source contributions

Publications

Collaboration

Education

MSc/MEng or PhD in ML/CS

Tools

PyTorch

Jax

Job description

The Institute of Foundation Models is seeking a Research Scientist to advance reinforcement learning methods for foundation models. You will prototype novel learning-from-experience approaches, contribute to large-scale training systems, and produce replicable, public code with collaborators.

You will build a productive research portfolio, publish in top venues, and engage with the open-source community while representing the lab at major conferences.