Research Engineer (Reinforcement Learning)

📋 Description

• Build training environments, verifiers, and supporting infrastructure for post-training models.
• Own synthetic data pipeline from data generation through QA and validation.
• Run end-to-end training experiments, analyze results, identify factors driving improvements.
• Design and maintain evaluations for production releases.
• Select and adapt open-weight foundation models for agent/product needs.
• Develop trained behaviors for voice and text-based agents.

🎯 Requirements

• Strong Python engineering skills to build reliable, production-quality systems.
• Experience moving ML models from raw data through experimentation to production.
• Data-centric mindset focusing on coverage, quality, and data leakage prevention.
• Ability to anticipate reward exploitation and design robust rewards, verifiers, and evaluation
• Practical experience with GPUs and understanding their capabilities/limits.
• Judgment on when modeling is right vs simpler approaches.

🎁 Benefits

• Opportunity to make a significant impact on a fast-growing developer platform.
• Collaboration with a small, experienced team that values excellence, creativity, and ownership.
• Competitive salary and equity package.
• Health, dental, and vision benefits.
• Flexible vacation policy.
• Remote-friendly environment with flexibility and autonomy.