Senior ML Engineer, Manipulation
Job Location:
San Francisco, CA - USA
Yearly Salary:
Posted:
Application Deadline:
Vacancies:
Job Summary
Chef Robotics is bringing AI into the physical world starting with one of the worlds largest industries: food manufacturing.
Food production faces one of the most severe labor shortages in the US with more than 1 million open jobs today and demand continuing to grow. Our robots help manufacturers automate repetitive food-preparation and assembly tasks so they can increase throughput improve consistency and keep production onshore.
Today Chef robots operate in production facilities across North America and Europe serving customers including Amys Kitchen gategroup and CookUnity. Our robots have made over 100 million servings in production creating the worlds largest proprietary dataset for AI-powered manipulation of deformable food. Every meal our robots produce makes the system smarter.
Backed by leading investors including Avataar Ventures Construct Capital Bloomberg Beta Promus Ventures and Kleiner Perkins were scaling rapidly with a robotics-as-a-service (RaaS) model and long-term customer partnerships. Our team includes engineers and leaders from Google Cruise Tesla Amazon Robotics Dexterity Bear Robotics Saildrone and Zoox united by a mission to build intelligent machines that solve meaningful problems in the real world.
If youre excited about solving hard problems creating real customer impact and shipping systems that operate in production every day not just in the lab youll feel at home at Chef.
About the Role
Chef Robotics is building autonomous robots that work alongside humans in commercial food preparation environments. Manipulation is one of the hardest open problems in robotics and food makes it harder. Unlike structured industrial parts food items are deformable visually similar irregularly shaped and behave differently depending on temperature moisture and preparation state. At Chef were solving this in production every day across a growing menu of meal types and preparation configurations.
As a Senior ML Engineer Manipulation you will own the learning systems that enable our robots to reliably pick place and handle diverse food classes using multiple end effectors from suction grippers to multi-finger hands. You will work end-to-end: from defining data collection strategies and training policies to deploying and debugging those policies on physical robots in real environments.
We are a small high-ownership team. We work onsite five days a week and move with startup urgency.
- 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 Chefs 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
- 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
- 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
Chef Robotics is solving one of the hardest problems in AI: bringing intelligence into the physical world.
Our robots are already operating in production facilities every day generating the real-world data that powers the next generation of embodied AI. If you want to build technology that leaves the lab ships to customers and transforms an industry Chef is the place to do it.
Required Experience:
Senior IC
