NEWHR 3 часа назад
Software Engineers, Robotics Controls
- London, UK
- В офисе
- Полная занятость
PythonCI/CDGitC++ROS2Real-time streamingmessage recording and replayrobotics middleware
Описание
Responsibilities
- The goal is to give operators safe, precise, confident real-time control of the robot: to guide it through a task, recover it when something goes wrong, teach it, and improve how it behaves.
- Take raw, noisy operator input and turn it into smooth, stable motion that stays within what the robot can physically do and behaves the same way every time.
- Connect VR controllers, gloves, haptics, motion capture, and custom control stations to the robot’s software.
- Decide how controls map to robot motion, what the operator sees and gets back as feedback, and how they recover the robot after a failure.
- Build modes that combine what the operator intends with what the robot can do on its own, so control becomes more precise, safer, and easier.
- Define safe operating limits and constraints, warnings, emergency and recovery procedures, and clear indication of the robot’s state.
- Build infrastructure including real-time streaming, calibration, session recording and replay, logs and debugging tools, operator training, and recording demonstrations clean enough to train models on.
- Define and improve quality metrics, such as delay, reliability, observability, how often operators complete tasks, the quality of recorded demonstrations, and how the system fails.
- Push the system to its limits in simulation and on real robots, and make it more reliable based on what operators report and what breaks.
- Work with the controls, manipulation, hardware, and operations teams so that remote-control needs shape both the robot’s design and how it’s used on site.
- Own how control quality is measured, on each robot and across the fleet.
- Replace gut feeling with hard numbers that show whether a release beats the last one, robots behave alike, and a fleet is ready for a customer pilot.
- Create test suites that show whether a given robot, and the fleet overall, reaches the target level of control performance.
- Build control assessment into the CI pipeline for both simulated and hardware-in-the-loop runs, with pass/fail criteria.
- Develop automated test setups that assess each control release deterministically.
- Take what engineers worry about, such as smoothness, latency, tracking error, and accuracy, and express each one as a precise, calculable metric.
- Build pipelines that derive these metrics in a uniform way from logged robot data, simulation, and live telemetry.
- Own the metric definitions and their versions, so that a value recorded now can be set against the same value half a year later.
- Let engineers compare controller variants and releases against each other directly.
- Follow how control behaves across months and across units: drift, unit-to-unit spread, and gradual degradation.
- Own the chain from the robot to the final figure, including dashboards that give a readable picture of the state of control.
Requirements
- You’ve worked hands-on with physical robots.
- You know what robot data looks like, why timestamps and synchronization matter, and where experiments on hardware tend to fall apart.
- A firm grasp of the basics: kinematics, reference frames, how control interfaces work, the essentials of state estimation, and how systems behave under real-time constraints.
- You write dependable code in C++, Python, or both.
- Familiarity with ROS/ROS2 or other robotics middleware, and with streaming data in real time.
- You can trace a problem through every layer: input devices, sensors, network, robot motion, and the physical hardware.
- You care about engineering quality: well-designed abstractions, test coverage, logs and observability, and tooling that doesn’t fall apart when the pressure is on.
- Fast hands-on cycles with real robots suit you, and you know how to take a prototype to a dependable feature.
- You communicate clearly and are used to working closely with neighboring teams.
- Good level of English — at least Upper-intermediate (B2).
- For Teleoperation, you have practical background in at least some of the following: remote-control systems for robots, operator interfaces, shared autonomy, human–robot interaction, or pipelines that collect data for robot learning.
- For Teleoperation, you have a feel for the human side of the loop: how operators read robot state, give commands, recover from mistakes, and come to trust the system.
- For Control Quality, you have developed test automation, evaluation frameworks, or benchmarking infrastructure, and gotten engineers to adopt them.
- For Control Quality, you have a sound understanding of measurement and data: sampling, noise, statistical significance, and telling a real difference between two runs from random variation.
- For Control Quality, you have hands-on experience with CI/CD and Git workflows, recording and replaying robot messages, robotics data formats, and time synchronisation.
Nice to have
- Experience building or debugging software for physical robots (manipulation, mobile manipulators, humanoids, dexterous systems), including safe operating procedures where lag, instability, poor feedback or misuse create risk.
- You've worked with operator-side technology such as haptics, force feedback, motion capture, VR/AR, intent prediction or custom control devices, and collected demonstrations for imitation learning.
- You care that control feels natural and safe for the person using it, not just that the robot moves.
- Enough knowledge of kinematics, dynamics or control theory to discuss the substance of what’s being measured, plus hands-on testing on hardware-in-the-loop benches and physical robots.
- Experience with MuJoCo or Isaac Sim/Lab and checking how simulation results carry over to real robots.
- You've run a fleet of robots or other distributed devices, done data engineering (pipeline orchestration, time-series storage, large-scale log processing), or release management and quality gates for safety-critical software.
We offer
- Competitive salary + stock options.
- Modern office at the heart of London with dedicated robotics labs and free meals.
- Skilled Worker visa sponsorship and relocation assistance.
- 23 days of annual leave, UK bank holidays, and company-wide days off.
- Private medical insurance and paid sick leave.
- Pension scheme, 8% total contribution.
- Close collaboration with the founding team and real impact on the product from day one.