Perception Engineer, Robot Safety

Job description

About Tutor We believe robots will be the next chapter in making physical labor safer and more affordable. But, nearly nine out of ten American factories and warehouses don’t have a single robot. Tutor Intelligence is changing that. We build robots that go straight into real factories and warehouses, to do real work, with real impact. Our robot Cassie does back-breaking work, moving boxes, pallets, and bulk goods for family-owned manufacturers to some of the largest brands in the world. Our robot Sonny does handwork, using two arms to achieve human-like dexterity in picking and packing. Every robot learns on the job, and each one we deploy makes the next one more capable, more affordable, and faster to put to work. Founded at MIT and headquartered in Watertown, MA, we do it all in-house: the robotics hardware, the machine learning, and the field deployment and service. We’re a team of researchers, engineers, technicians, operators, and sellers who love building things and solving hard problems. Our mission is grand: robots everywhere, for the common good, raising the standard of living across North America, and then the world. The Role Our robots work in customer facilities with people nearby. The systems that keep those people safe are perception systems: sensors that detect a person, and software that decides how the robot responds. We're looking for an engineer to build those systems and own the code they run on. This is an engineering role. You will design and build perception and monitoring systems, own safety-critical code end to end, and be responsible for the design and review of the systems that decide whether a robot may move. You will work across our product teams, joining whichever one is building something that affects safety, and you will test our systems for weaknesses before they show up in the field. You will also help shape how Tutor keeps its robots safe and deployable. A robot that hurts someone is unacceptable, and a robot that cannot be deployed where the work is does not help anyone. The formal side of safety, risk assessments and the standards customers ask about, is part of this role. We will teach it. We are hiring for the engineering. What You'll Do Build the perception systems that keep people safe: Detection, tracking, and monitoring from lidar and cameras, running on robots in production Own safety-critical code: The software path from a sensor reading to a stopped robot, including its tests, its failure modes, and its behavior when something upstream fails Design and review safety-relevant systems: Set the design for how a robot decides it is safe to move, and review changes across the codebase that affect that decision Test for weaknesses: Use replayed field data, constructed scenarios, and hardware faults to find where the system fails, and fix what you find Work across product teams: Join the team building something that affects safety and build it with them Help set the strategy: Contribute to how Tutor keeps its robots safe and deployable as the fleet and the applications grow, including the evidence we give customers What We're Looking For Experience shipping perception or monitoring software on robots or vehicles: Lidar or camera pipelines, detection, tracking, or sensor fusion, running on hardware in production You have owned code where a bug could injure someone: You know how that changes design, testing, and review Strong software engineering: Python and C++ or similar, real-time constraints, and code that other people can verify Some controls knowledge: Stopping distances, latency budgets, and how a perception decision becomes a motion command You fix what you find: When you find a weakness, you propose the fix and usually build it Nice to Have Exposure to safety standards for robots or machinery, such as ISO 10218, ISO 13849, or ANSI/RIA R15.06 Experience with safety-rated sensors or safety validation of a detector Experience in warehouses, manufacturing, or other environments where robots and people share space Simulation and replay tooling for testing perception at scale