Staff ML Engineer, Agent Training & Environments

📋 Description

• Build RL environments and harnesses for thousands of parallel experiments.
• Create verifiers and graders with rubrics and pass@k scoring at scale.
• Develop SFT and RL fine-tuning pipelines from data collection to evaluation.
• Run eval systems measuring model and product quality across trajectories.
• Build scalable training and serving infra: multi-launchers, fault tolerance.

🎯 Requirements

• 3+ years shipping production systems used by customers and engineers.
• Deep proficiency in Python; strong API design and systems thinking.
• Experience building agent environments and post-training RL/SFT pipelines.
• Ship reliable production code for AI agents and APIs; strong design.
• Build tooling, CI, and harnesses; own substrate others rely on.
• Thrives in ambiguous startup environments with ownership and influence.

🎁 Benefits

• Location: SF tech hub; hybrid model with 3 days in office.
• Fast-paced environment with ownership and rapid impact.
• Growth opportunities directly tied to your impact.
• Pay parity and transparent compensation discussions.
• Join a mission to build AI foundations for humanity.
• Collaborative team of researchers and engineers.