Member of Technical Staff RL Inference

You will design and optimize inference systems for reinforcement-learning workloads, from small-scale ablations through production training runs. You will analyze performance bottlenecks and work with modeling specialists to implement new reinforcement-learning techniques and algorithms efficiently.

Responsibilities

• Design and optimize the inference stack for reinforcement-learning workloads.
• Analyze, profile, and address performance bottlenecks in large-scale reinforcement-learning systems.
• Implement novel reinforcement-learning techniques and algorithms efficiently.

Requirements

• Experience building, debugging, and optimizing large-scale distributed systems.
• Experience in LLM inference.
• Proficiency in Python, C++, or Rust.
• Knowledge of PyTorch, JAX, or CUDA.

Benefits

• Equity
• Medical coverage
• Vision coverage
• Dental coverage
• 401(k) retirement plan
• Short-term disability insurance
• Long-term disability insurance
• Life insurance
• Discounts and perks