Senior ML Engineer, Manipulation

Chef Robotics is accelerating the deployment of intelligent machines in the physical world, starting with food production — the sector facing the largest labor shortage in the U.S., with 1.14M unfilled jobs today and 3.1M projected by 2030. These roles can't be offshored, making robotics essential to keeping production onshore and strengthening America's manufacturing base.

Our AI-powered robots automate food prep and assembly in commercial kitchens and food manufacturing, and have already produced over 110 million meals in production — generating the world's largest proprietary dataset for deformable food manipulation. Backed by investors including Kleiner Perkins, Construct, Bloomberg Beta, and Promus Ventures, and built by a team from Cruise, Zoox, Google, Tesla, and Amazon Robotics, Chef is rapidly scaling with multiple multi-year contracts and a mission to put an intelligent robot in every commercial kitchen.

In this role, you will:

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; build recovery and fallback behaviors that handle dropped items, mis-grasps, and partial occlusions gracefully
Partner with perception and robotics engineers to validate end-to-end grasp-to-place performance across new food classes, and end effector configurations

What You Bring:

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

Nice-to-have:

Experience with Vision-Language-Action (VLA) models, diffusion policies, or transformer-based action representations
Familiarity with simulation environments (MuJoCo, Isaac Sim, Genesis) and sim-to-real transfer techniques
Experience with multiple end effector types — suction, parallel jaw, multi-finger, or soft grippers
Background in food, agriculture, or consumer goods robotics where object variability is high
Experience with model compression, quantization, or TensorRT for edge deployment
Contributions to open robotics datasets or publications at CoRL, ICRA, RSS, NeurIPS, or similar venues
Experience using simulation environments (e.g. Isaac Sim, Gazebo) for synthetic data generation and domain randomization