Director of Reinforcement Learning

Job Summary

A company is looking for a Director of Reinforcement Learning (RLHF).

Key Responsibilities

• Set the RLHF vision and roadmap, identifying high-impact opportunities for improvement
• Lead the design and development of RLHF systems, including reward modeling and policy optimization
• Build and lead a high-performing RL team, fostering a culture of excellence and continuous learning

Required Qualifications

• Master's degree with 10-12+ years or Bachelor's degree with 12-14+ years in Computer Science, IT, or related field
• Deep expertise in Reinforcement Learning from Human Feedback (RLHF) and advanced reinforcement learning
• Experience deploying RLHF or RL systems into production for real-world applications
• Strong background in modern machine learning, deep learning, and proficiency in Python and frameworks like PyTorch or TensorFlow
• Demonstrated ability to lead technical teams, manage projects, and communicate complex topics to non-technical stakeholders