Robotics Research Engineer, Teleoperation

Weave was founded to build the robots we’d want to have in our own home. We believe the next generation of robotics will transform everyday life by enabling people to do more and to reclaim time to spend on what’s important.

We also believe robots are in a sense like any other product: to matter, they have to ship. Our robots are already operating in real homes and businesses, giving us the opportunity to rapidly improve from real-world experience. With a growing team, strong customer demand, and capital for expansion, we’re entering an exciting stage of growth—and we’re looking for people with exceptional talent and standards to help bring home robotics to millions of households.

What can be teleoperated can be learned. Teleoperation sets the floor on our robots' dexterity: whatever an expert operator can do through the robot is something our robots can do today, and something our models can learn tomorrow. We intend that floor to be the highest in the world.

Getting there is an HCI, sensing, ergonomics, and robotics problem all at once. You’ll own the system end to end. You'll work closely with our mechanical, robotics, and software teams to ensure our robots can be operated to the full extent their hardware allows: seamlessly mapping human motion into bimanual robot motion, over real networks.

• Build the operator's visual interface. Applications for teleoperation: stereo video rendering inside motion-to-photon budgets, overlays for robot state and intent, and interface design that keeps operators oriented during long sessions, including for VR.

• Own the input layer. Integrate and evaluate headsets, various controllers, and our leader hardware, and decide which input maps to which robot capability, partnering with the engineer building our leader devices.

• Drive retargeting. Map operator motion to robot motion that respect the robot's limits while preserving the operator's intent, for both arms, torso, and base together.

• Hide latency. Prediction, local simulation, and interpolation on the operator side so perceived delay stays below what operators notice, even when the physical loop is 60 to 150 ms.

• Build shared autonomy. Blend operator input with autonomous assistance so that novice operators approach expert throughput and takeover between model and human is seamless in both directions.

• Spec the operator station. Set the requirements for input rigs, displays, and full-shift ergonomics. Your findings drive what we build and who we hire next.

• Ship it. Operators will use your systems every day. A tight iteration loop will make sure your research moves as fast as possible while having real world impact.

• 3+ years in teleoperation, haptics, or closely allied control research. Publications welcome, but working systems in real settings count just as much.

• Interactive systems competence. You've built VR, simulation, or game-engine software, or you're demonstrably able to own an operator-facing 3D interface.

• Depth in the delay problem: you can explain when passivity-based methods are too conservative, what time-domain passivity buys you, and why a stable system can still feel dead.

• Strong optimization-based control: differential IK, QP formulations, constraint handling at interactive rates.

• Systems fluency: you profile end-to-end pipelines across device, network, and robot, and you respect where the milliseconds actually go.

• Operator empathy. You’re hands-on and empirical as you refine your own system–both using it yourself and learning from others who do.

• Surgical robotics, humanoid teleop, or haptics lab lineage: Bilateral systems or academic haptics.

• Excellent software engineering skills: Experience writing production-quality software in C++.

• Shared autonomy or learned assistance publications or systems.

• Experience where teleop fed a learning pipeline and data quality was a first-class concern.