Before you apply
Listed location: Menlo Park, CA; Montreal, Canada
Work arrangement: onsite. A remote label does not confirm worldwide eligibility or visa sponsorship.
Read the employer’s description for qualifications, compensation and work eligibility. Confirm the position is still open on the application page.
Job description supplied by Periodic Labs; category and skill labels may be inferred. How our listings work · Report a problem
Job Description
About Periodic Labs
We're an AI and physical sciences company building state-of-the-art models to accelerate breakthroughs across materials, energy, and beyond. Backed by world-class investors and growing rapidly, we operate at the pace the frontier requires. Our team brings deep expertise, genuine ownership, and a drive to push the boundaries of what's scientifically possible.
About the Role
We're training frontier models to develop deep scientific knowledge and reasoning for scientific tasks. You’ll study how RL scales with training compute, develop better algorithms, and take ideas from controlled experiments to our largest runs like Periodic Neon.
What You'll Do
Design experiments to understand how RL performance scales with compute, model size, data, and reward quality, building on work such as ScaleRL
Develop better RL algorithms, spanning policy optimization, advantage estimation, exploration, and credit assignment for long-horizon RL tasks
Build adaptive sampling and curriculum methods that adjust task difficulty, problem selection, and the number of rollouts as models improve
Study bias and stability during RL training, including importance-sampling corrections and methods to tackle policy staleness and training–inference mismatch, as discussed here.
Improve compute efficiency across training and inference through experiments with hyperparameters, such as length penalties, rollout counts, batch sizes, and update schedules.
You Will Thrive in This Role If You Have
Hands-on experience training LLMs with reinforcement learning
Strong attention to detail and rigorous approach to answer questions scientifically.
Coming up with small-scale RL setups that transfers to large-scale training runs.
Comfort working across a complex training stack to implement, debug, and test new research ideas.
We are open to offering a 1 year post-doc for this profile. Early career (final year PhD students) are encouraged to apply.
Mechanics
Minimum education: Bachelor’s degree or similar experience
Location: Menlo Park, CA or Montreal, Canada
Compensation: $225,000-$350,000 base + equity
Visa sponsorship: Yes, we sponsor visas and will do everything we can to assist in this process.
Skills mentioned
Categories
Frequently asked questions
Is the Research Scientist, Scaling RL position at Periodic Labs remote?
The Research Scientist, Scaling RL role at Periodic Labs does not have a confirmed remote arrangement in our data. Check the employer description for its work location.
What type of employment is the Research Scientist, Scaling RL role?
Periodic Labs is hiring for a full-time Research Scientist, Scaling RL position.
Which skills are mentioned for the Research Scientist, Scaling RL job at Periodic Labs?
Detected skill labels include Reinforcement Learning. Check the employer description to distinguish required skills from preferred experience.
How do I apply for the Research Scientist, Scaling RL position at Periodic Labs?
You can apply for the Research Scientist, Scaling RL role directly through Periodic Labs's official application link provided on this page.
Similar AI jobs
ML Research Scientist, Active Learning
Nuro · fulltime
research engineer
Turbopuffer · fulltime
Research Engineer, AI Monitoring
Anthropic · fulltime
Researcher, Frontier Robustness
OpenAI · fulltime
Staff ML Research Engineer, Multimodal Structure & Marengo
Twelve Labs · fulltime
Applied Research Scientist Intern, Agentic Biology - Summer 2027
NVIDIA · fulltime