Research Scientist, Scaling RL
About this role
Research Scientist, Scaling RL is an opening located in Menlo Park, California or Montreal, Canada, designed for a professional focused on scaling reinforcement learning for frontier models. This position fits candidates experienced in training large language models using reinforcement learning who want to advance scientific knowledge and reasoning tasks.
Role Overview
Periodic Labs seeks a Research Scientist, Scaling RL to join the team in Menlo Park, CA or Montreal, Canada. The position centers on training frontier models to develop deep scientific knowledge and reasoning capabilities. The professional in this role will investigate how reinforcement learning scales alongside training compute, create improved algorithms, and transition experimental concepts into large-scale runs.
Key Responsibilities
Requirements
Skills and Tools
Salary and Benefits
About the Company
Periodic Labs operates as an artificial intelligence and physical sciences organization focused on constructing models to speed up breakthroughs in materials, energy, and related fields. Supported by investors, the organization expands rapidly and maintains a team possessing technical expertise and ownership.
How to Apply
Interested candidates should apply directly on the official company careers page.
Skills and tech stack
Questions candidates ask
Where is the Research Scientist, Scaling RL position located?
The role is based in Menlo Park, CA or Montreal, Canada.
What is the salary range for this job?
The base compensation is between $225,000 and $350,000, plus equity.
Is visa sponsorship available?
Yes, visa sponsorship is provided with assistance offered throughout the process.
What minimum education is required?
A Bachelor's degree or similar experience is required.
What is the primary focus of the work?
The work involves training frontier models for scientific knowledge and reasoning, studying reinforcement learning scaling with compute, and developing improved algorithms.