Robotics Perception Engineer job description template
A robotics perception engineer gives robots the ability to sense and interpret their surroundings well enough to act — localising, mapping, detecting objects and estimating grasp poses. The work sits between computer vision and robotics, and always runs on constrained on-robot hardware.
Before you post
Describe the robot and the environment concretely. Candidates for this role are choosing a problem domain as much as a company, and "warehouse AMR operating around people" tells them far more than "cutting-edge robotics platform". Mention your logging and simulation infrastructure — experienced engineers know it determines their quality of life.
The template
About the role
We are hiring a robotics perception engineer to build the sensing stack for [robot / platform]. You will make our robots reliably understand [environment] using [sensor suite], on the compute available on board.
What you will do
- Develop perception components for localisation, mapping and object detection
- Integrate and calibrate sensors across the platform
- Optimise perception to run within on-robot compute and power budgets
- Debug field failures from logged data and improve robustness
- Build test coverage across simulation and recorded scenarios
What we are looking for
- Strong C++ and Python
- ROS or ROS 2 experience
- Practical experience with SLAM, localisation or 3D perception
- Experience working on physical robots, not only in simulation
Keep this list to three to five items. Long mandatory lists disproportionately deter the candidates you most want.
Nice to have
- NVIDIA Jetson or similar embedded deployment
- Experience in [your environment — warehouse, field, outdoor]
- Manipulation and grasp pose estimation
- Simulation experience with Gazebo or Isaac Sim
Plain text version
Select all and paste into your ATS, then replace everything in brackets.
ROBOTICS PERCEPTION ENGINEER ABOUT THE ROLE We are hiring a robotics perception engineer to build the sensing stack for [robot / platform]. You will make our robots reliably understand [environment] using [sensor suite], on the compute available on board. WHAT YOU WILL DO - Develop perception components for localisation, mapping and object detection - Integrate and calibrate sensors across the platform - Optimise perception to run within on-robot compute and power budgets - Debug field failures from logged data and improve robustness - Build test coverage across simulation and recorded scenarios WHAT WE ARE LOOKING FOR - Strong C++ and Python - ROS or ROS 2 experience - Practical experience with SLAM, localisation or 3D perception - Experience working on physical robots, not only in simulation NICE TO HAVE - NVIDIA Jetson or similar embedded deployment - Experience in [your environment — warehouse, field, outdoor] - Manipulation and grasp pose estimation - Simulation experience with Gazebo or Isaac Sim ABOUT US [Two or three sentences on the company, the product, and why the problem matters.] DETAILS - Location: [city / hybrid / remote] - Salary: [range] - Apply: [link]
Calibrating the level
Adjust the requirements to match the level you are actually hiring for. Asking for senior capability at a mid-level budget is the most common cause of a stalled search.
Junior
Implements perception nodes and tunes them against recorded bags.
Mid
Owns a perception capability on the robot and its behaviour in the field.
Senior
Designs the perception stack and decides the sensor configuration.
Staff / Principal
Owns autonomy architecture and the trade-offs between sensing cost and capability.
Post it where the right people are
JobsInVision is a computer vision job board — your listing reaches engineers who work in this field specifically, rather than a general software audience.