Research Engineer (Reinforcement Learning)

📋 Description

• Build training environments, verifiers, and infra for post-training models.
• Own the synthetic data pipeline from generation to QA and validation.
• Run end-to-end training experiments and analyze results.
• Design evaluations models must pass before prod releases.
• Adapt open-weight foundation models for agent needs.
• Develop behaviors for voice and text-based agents.

🎯 Requirements

• Strong Python engineering and production systems.
• ML model lifecycle: data to production experience.
• Data-centric mindset: coverage, quality, leakage care.
• Design robust rewards, verifiers, and evals.
• Experience with GPUs and training constraints.
• Judgment on when training is right vs simpler approach.

🎁 Benefits

• Impact on fast-growing dev platform.
• Small, experienced team with ownership.
• Competitive salary and equity.
• Health, dental, vision benefits.
• Flexible vacation policy.
• Remote-friendly environment.