Research Engineer in Reinforcement Learning

Job Summary

Focusing on the development of novel environments and training pipelines, the full-time Research Engineer in Reinforcement Learning will operate remotely to advance AI capabilities through scalable, high-performance systems and automated evaluation processes.

Key responsibilities

• Architect self-contained RL environments that capture complex, real-world tasks
• Design and scale episode pipelines and multi-component training processes for reproducible experimentation
• Develop automated data generation systems and integrate AI-driven evaluation and quality assurance systems

Required qualifications

• Deep experience in Reinforcement Learning, including environment design and training dynamics
• Strong track record of building and scaling RL systems or experimentation frameworks
• Proficient in automation and synthetic data generation pipelines
• Experience with automated evaluation systems and model validation workflows
• Skilled in fine-tuning and evaluating open-source ML models