New

Robot Systems Integration Engineer

mid
Software EngineeringIntegration Developer
2 views0 saves0 applied

Quick Summary

Key Responsibilities

gesture, head and torso orientation for gaze, posture, locomotion-in-place, and safe transitions between them, timed to speech. Expose the robot to the application layer as a small,

Requirements Summary

RWS Holdings PLC does not accept agency resumes. Please do not forward any unsolicited resumes to any RWS employees. Any unsolicited resume received will be tre

Technical Tools
Software EngineeringIntegration Developer

About the Role

~1 min read

 

You own two things: the robot, and the devices we collect data with.

The robot is a commercial humanoid that interacts with people in real venues. It arrives as hardware and an SDK; you make it a platform the rest of the team can build on: gesture, gaze and posture under software control, clean sensor streams out, a safety envelope for standing next to strangers, and a robot that is ready every morning of a demo.

The devices are the capture kit we use to record people and robots for training data: fisheye cameras, wrist-worn IMU and hand-pose sensors, lightweight RGB-D, and the robot’s own sensors. You integrate them, keep them time-synced and calibrated, and keep them running at collection sites.

You are the lowest layer of a small engineering team. An application engineer builds speech, dialogue and the operator console on the interfaces you expose; a hardware engineer designs the capture rigs you integrate. You work daily with the platform maker’s developers, and you are the person who knows what the robot can and cannot do.

 

RWS TrainAI is the AI data and evaluation business of RWS Group, working with leading AI developers worldwide. We are building a physical AI practice: multilingual, culturally localized interaction for service robots, human evaluation of how robots behave around people, and the data pipelines behind both. Our advantage is a global, multilingual human network and a focus on behavior that is culturally appropriate, measured and auditable.

Responsibilities

~1 min read

 

  • Build and maintain the robot control layer using the platform’s SDK (DDS-based) and ROS 2 on NVIDIA Jetson: gesture, head and torso orientation for gaze, posture, locomotion-in-place, and safe transitions between them, timed to speech.
  • Expose the robot to the application layer as a small, stable API: behavior primitives (greet, turn toward, point, beckon, hold a conversational posture, hand off) and a sensor event stream (speaker direction, person detected, approach distance, face and gaze).
  • Get raw microphone and camera streams off the robot at the latency the speech and perception pipeline needs; work with the maker’s developers on access the SDK does not yet give.
  • Own firmware and SDK updates, calibration, battery and thermal management, emergency stop and recovery, and the safety envelope for a humanoid among the public: speed and force limits, keep-out distances, what the robot does when touched.
  • Integrate capture sensors with their device SDKs and firmware, with hardware time sync across modalities, and execute the calibration protocol set by the hardware engineer.
  • Record demonstration and teleoperation data from the robot itself (joint states, cameras, audio) in the format the data pipeline expects.
  • Write the test plan for each venue, run it on site, and triage what fails: document, reproduce, fix or hand off across hardware and software.
  • Instrument the robot and devices with health telemetry and a daily readiness check a colleague can run without you; send a weekly site-health summary to engineering.
  • Package the platform layer so a second robot, in another location, comes up from a known configuration in a day, and write the runbook that goes with it.

 

Requirements

~1 min read

 

Get the 3Ps right – Partner, Pioneer, Progress – and we´ll Deliver together as RWS.

 

Recruitment Agencies: RWS Holdings PLC does not accept agency resumes.  Please do not forward any unsolicited resumes to any RWS employees.  Any unsolicited resume received will be treated as the property of RWS and Terms & Conditions associated with the use of such resume will be considered null and void.

  • 3+ years building software that ran on real robots in the real world, not simulation alone.
  • Hands-on experience with a commercial humanoid or legged platform: deploying, debugging and controlling it through the maker’s SDK, ROS 2 and NVIDIA Jetson, including joint and posture commands and trajectory timing.
  • Strong C++ and Python; comfortable with DDS or similar middleware, Linux, real-time constraints and embedded compute.
  • Experience getting sensor data (cameras, microphones, IMU) off a robot or device and into a software pipeline, with hardware time synchronization.
  • Comfortable debugging hardware under deadline and running a robot safely around members of the public.
  • Native-level Mandarin and professional working English; eligible to work in China.

Nice to Have

~1 min read
  • Multi-sensor calibration (camera intrinsics and extrinsics, IMU, depth) and wearable or egocentric capture hardware.
  • Teleoperation or motion-capture rigs, and recording demonstration data for robot learning (LeRobot, RLDS or similar conventions).
  • Humanoid foundation-model stacks (e.g. NVIDIA Isaac GR00T or a robot maker’s open models) or a robot maker’s developer ecosystem.
  • Gesture retargeting from motion capture or animation, or working with animators.
  • Functional safety or risk assessment for collaborative or mobile robots.
  • Robots that interact with the public: retail, museums, hospitality, healthcare, education.
  • SLAM, localization and navigation on a mobile or legged robot, or real-to-sim capture and reconstruction (LiDAR scanning, photogrammetry, Gaussian splatting). Autonomous navigation and venue simulation come later in the program, and the platform layer you own is where they land.

 

  • First month: robot up in a real venue with the SDK integrated; greet, turn-toward and point primitives callable from the application layer; raw audio and camera streams at usable latency.
  • First 3 months: a live, multilingual interaction demo on the real robot in front of an audience. Not polished: the robot greets, turns toward, points and hands off with gesture and gaze timed to speech in two languages, with an operator in the loop; zero safety incidents; robot available on every scheduled demo day.
  • By 6 months: capture devices integrated with cross-modality sync drift inside the agreed tolerance; a second robot brought up in another location from your packaged configuration in one day; readiness check and runbook in use without you present.

 

Location & Eligibility

Where is the job
Not specified
Location terms not specified

About this job

Posted
1 day ago
Employer
has 27 open jobs on Jobera.

Listing Details

Posted
November 18, 2026
First seen
November 19, 2026
Last seen
November 19, 2026

Posting Health

Days active
0
Repost count
0
Trust Level
49%
Scored at
November 19, 2026

Signal breakdown

freshnesssource trustcontent trustemployer trust
Newsletter

Stay ahead of the market

Get the latest job openings, salary trends, and hiring insights delivered to your inbox every week.

A
B
C
D
Join 12,000+ marketers

No spam. Unsubscribe at any time.

Robot Systems Integration Engineer