Chef Robotics is on a mission to accelerate the advent of intelligent machines in the physical world, starting with food. We build AI-powered robots that assemble fresh meals at scale for some of the largest food producers in North America — companies making ready-to-eat meals for airlines, retailers, meal kits, and the frozen food aisle.
Our robots operate in high-mix, high-variability production environments where ingredients change shape, color, and consistency from one tray to the next. Solving this requires tightly coupled perception, manipulation, and learning — and a team that ships hardware-software systems into customer facilities and keeps them running.
Headquartered in San Francisco, we are a venture-backed team of robotics, ML, and operations engineers building the foundation for general-purpose food robotics.
About the Role
As a Staff Autonomy Engineer, you will own the technical architecture of Chef's autonomy stack end-to-end — from perception and action prediction through closed-loop control and production deployment. This is a hands-on technical leadership role: expect to spend the majority of your time designing and building, with the remainder setting direction, mentoring engineers, and driving cross-functional alignment. You will report directly to the engineering leadership and have direct influence over how Chef's autonomy systems scale across a growing commercial fleet.
We are a small, high-ownership team. We work onsite five days a week and move with startup urgency.
In this role, you will:
- Own the end-to-end architecture and hands-on development of Chef's autonomy stack — perception, action prediction, closed-loop control, and sensor fusion — from prototype through production deployment
- Design and implement learning-based systems that predict and execute robot actions from visual and operational observations, generalizing across diverse ingredient types with minimal per-item tuning
- Build closed-loop control systems that integrate vision, weight feedback, force-torque sensing, and trajectory planning for robust real-world manipulation
- Develop rapid onboarding capabilities — algorithms and tooling that enable new meal types and ingredient configurations to be deployed quickly from minimal demonstrations
- Instrument autonomy systems for production monitoring, failure detection, and continuous improvement; build data collection pipelines that feed back into model retraining
- Define objective qualification criteria for autonomy subsystems; drive reliability and performance improvements using production data across the deployed fleet
- Investigate and integrate the latest advances in robot learning, foundation models, and manipulation research — continuously evaluating what's ready to move from research into production
- Mentor senior engineers, lead design reviews, and help build a team capable of scaling Chef's autonomy stack to hundreds of deployed systems
What You Bring:
- Demonstrated experience shipping a complete autonomy or manipulation system to real-world deployment — not just simulation or research prototypes
- Deep technical expertise across at least two of: perception systems, visuomotor control, action prediction, sensor fusion, or motion planning
- Strong software engineering fundamentals in Python and C++; experience building production-quality, maintainable systems across research and deployment codebases
- Track record of technical leadership: driving architecture decisions, leading cross-functional projects, and raising the engineering bar on a team
- Comfort with ambiguity and urgency — able to set direction and execute in a fast-moving startup environment
Nice-to-have:
- Experience with food, agricultural, or consumer goods robotics where object variability is high
- Experience with ML frameworks (PyTorch preferred) and the full model lifecycle — training, evaluation, deployment, and field iteration
- Familiarity with foundation model approaches for manipulation: diffusion policies, VLAs, world models, JEPA-style architectures
- Background in sim-to-real transfer, domain randomization, or synthetic data generation for manipulation
- Experience with ROS and real-time robotics middleware
- Prior startup technical leadership experience
