Research Engineer (Reinforcement Learning)

📋 Description

• Build training environments, verifiers, and infra for post-training models.
• Own synthetic data pipeline from generation to QA/validation.
• Run end-to-end training experiments and identify factors driving improvements.
• Design evaluations models must pass before production releases.
• Select/adapt open-weight foundation models for agent needs.
• Develop trained behaviors for voice and text agents.

🎯 Requirements

• Strong Python engineering and production-quality systems.
• Experience taking ML models from data to production.
• Data-centric mindset: coverage, quality, leakage control.
• Ability to design robust rewards, verifiers, and evaluations.
• Experience with GPUs and understanding their capabilities/limits.
• Good judgment on when training is the right tool vs simpler approaches.

🎁 Benefits

• Opportunity to shape a fast-growing developer platform.
• Collaboration with a small, expert team valuing ownership.
• Competitive salary and equity package.
• Health, dental, and vision benefits.
• Flexible vacation policy.
• Remote-friendly environment with autonomy.