Senior ML Engineer, Manipulation

Job description

Job responsibilities

• Design and train manipulation policies — behavior cloning, imitation learning, and RL — for dexterous food handling across diverse item classes and end effector types (suction, parallel jaw, multi-finger)
• Implement and evaluate modern policy architectures (diffusion policies, transformer-based action models, action chunking) and adapt them to Chef's specific food manipulation challenges
• Work with the platform team to build data collection pipelines using teleoperation, kinesthetic teaching, and autonomous rollouts; work with the data team on dataset curation, augmentation, and training infrastructure
• Define evaluation metrics and regression benchmarks that accurately predict real-world manipulation performance;
• Partner with perception and robotics engineers to validate end-to-end grasp-to-place performance across new food classes, and end effector configurations

Job requirements

• MS or PhD in Robotics, Machine Learning, Computer Science, or a closely related field — or equivalent practical experience
• 5+ years of experience developing and deploying ML systems for robotics manipulation, visuomotor control, or robot learning
• Deep expertise in at least two of: imitation learning, reinforcement learning, grasp estimation, or learned motion generation
• Strong PyTorch skills and experience building reliable, production-quality training and evaluation pipelines
• Hands-on experience deploying policies to real robotic hardware — not just simulation results
• Strong software engineering fundamentals in Python; ability to write maintainable, well-tested code across research and production codebases
• Track record of owning projects end-to-end: from problem framing through field deployment and iteration