3 months ago
London, United KingdomSenior
Responsibilities
- Develop and maintain device software covering session initialization, sensor stream management, episode recording, and graceful shutdown.
- Integrate and synchronize camera, pose-tracking, gripper encoder, and optional force/torque sensor streams into temporally aligned trajectories.
- Define and maintain stream formats, episode packaging, metadata schemas, and interfaces between raw recordings and AI training pipelines.
- Build data validation tooling to detect dropped frames, timing jitter, pose tracking loss, image degradation, and sensor faults.
- Own operator-facing controls and feedback for starting, stopping, canceling, retrying, and reviewing collection sessions.
- Deploy devices during field data-collection sessions, validate data quality in situ, and iterate on issues.
- Debug camera drivers, bus bandwidth, tracker calibration, thermal throttling, and storage failures on device hardware.
Requirements
- Experience developing embedded or device-level software in robotics or sensing contexts.
- Proficiency in C++ and/or Python for real-time sensor drivers, inter-process communication, and data-recording pipelines.
- Understanding of multimodal sensor synchronization, timestamps, hardware triggers, and clock drift.
- Familiarity with camera pipelines and ensuring sensor data is recorded with correct timing.
- Strong focus on data quality and dataset hygiene, including frame drops, tracking loss, and stream alignment.
- Ability to debug real hardware using logs and profilers and distinguish driver, bus, and timing problems.
- Experience with 6-DOF pose tracking systems such as VIO or optical trackers is preferred.
- Familiarity with ML training-data formats and the needs of AI teams consuming recorded episodes is preferred.
- Experience with operator-facing collection tooling, session management, episode quality summaries, rejection and retry workflows, and scaling device software to field operators is preferred.
Benefits
- Competitive equity through stock options.
- 30+ paid days off, including annual leave, UK bank holidays, and company closure days.
- Private healthcare with virtual and in-person care.
- Pension scheme with an 8% total contribution, comprising 5% employee and 3% employer contributions, on full earnings.
- Free daily breakfast, catered lunch, and snacks in the office.
- Opportunity to work with engineering, research, and product teams on humanoid robotics and AI.
- Significant ownership and direct access to founding leadership.
