Research Engineer, Performance RL (Reinforcement Learning)

Overview

Research Engineer for the Code RL team, advancing models’ ability to safely write correct, fast code for accelerators.

What you'll do

• Invent, design, and implement RL environments and evaluations.
• Conduct experiments and shape the research roadmap.
• Deliver work into training runs.
• Collaborate with researchers, engineers, and performance engineering specialists across teams.

What you'll need

• Expertise with accelerator performance and accelerator technologies (CUDA, ROCm, Triton, Pallas).
• ML framework programming experience (JAX or PyTorch).
• Experience across the stack including kernels, model code, and distributed systems.
• Ability to balance research exploration with engineering implementation.
• Commitment to developing safe and beneficial AI systems.

Details

• Hybrid policy expects staff to be in an office at least 25% of the time.
• Visa sponsorship is available in some cases, with reasonable efforts to secure visas if offered.