Research Engineer

Research Engineer at Metis focused on building autonomous post-training systems using the Mantis platform. This role involves designing and implementing ML algorithms for AI agent learning from feedback, synthetic data, and real-world interactions, with a focus on reinforcement learning and preference optimization.

Skills and focus areas

• machine learning
• reinforcement learning
• post-training
• alignment research
• ml research
• scalable engineering
• algorithm design
• algorithm implementation
• algorithm deployment
• ai agents
• feedback learning
• synthetic data generation