Reinforcement Learning Researcher (AI)

Location: Menlo Park, California, United States; on-site

Base compensation: $250,000–$350,000 per year, plus equity

Company

Periodic Labs is an AI and physical sciences company developing models to accelerate breakthroughs in materials, energy, and related scientific fields.

What you will do

• Design experiments to study how reinforcement learning scales with compute, model size, data, and reward quality.
• Develop RL algorithms for policy optimization, advantage estimation, exploration, and credit assignment in long-horizon tasks.
• Build adaptive sampling and curriculum methods that adjust task difficulty, problem selection, and rollout counts.
• Investigate bias and stability in RL training, including importance-sampling corrections, policy staleness, and training–inference mismatch.
• Improve training and inference efficiency through experiments with hyperparameters, rollout counts, batch sizes, and update schedules.

Requirements

• Hands-on experience training LLMs with reinforcement learning.
• Ability to design small-scale RL setups that transfer to large-scale training runs.
• Experience implementing, debugging, and testing research ideas across a complex training stack.
• Strong attention to detail and a rigorous scientific approach to answering research questions.
• At least 5 years of experience.
• Bachelor’s degree or equivalent experience.

Culture & Benefits

• Work on frontier models for scientific reasoning and discovery.
• Collaborate in a rapidly growing, research-focused environment.
• Receive equity in addition to base compensation.
• Visa sponsorship is available, with assistance throughout the process.