Hiring nowAutonomous navigation and field robotics

Autonomy Perception Engineer

Also called Autonomous Systems Perception Engineer

An Autonomy Perception Engineer turns raw sensor data into a reliable picture of the world that a machine can act on. It decides whether an autonomous system sees, locates and tracks things accurately enough to be trusted.

What they do

Builds and maintains the perception subsystem of an autonomous system. Day to day, that means combining camera, lidar, radar, inertial and positioning data into one consistent estimate of where things are and where the machine is. Tunes tracking and filtering, handles sensor drift and dropouts, and checks timing and calibration. Runs the stack in simulation and on real hardware, reads the failures, and fixes the cause. Writes tests that cover lighting, weather, clutter and sensor faults. Works closely with planning and controls engineers on what they need from perception.

What a strong hire delivers

Within the first months, a strong hire gets the current perception stack measured, with clear error figures for detection and localisation inside the approved operating domain. They fix the largest failure modes, put calibration and timing on a repeatable footing, and build a test set and simulation scenarios that the team reruns after every change. Planning colleagues get outputs with honest uncertainty attached.

How you can tell they are good

Ask them to walk through a perception failure they diagnosed on real hardware. Strong people name the sensor, the cause and the evidence, not just the fix. Ask how they set the limits of an operating domain and how they test them. Ask how they represent uncertainty. Be wary of anyone who talks only about model accuracy and never about calibration, timing or edge conditions.

Why it is hard to fill

The title varies widely. The same work sits under perception, state estimation, localisation, sensor fusion and autonomy. Many candidates are strong in one piece, such as deep learning for vision or filtering theory, but have not owned a fused system running on hardware. The people who combine both are few, and most are already deep in a programme they do not want to leave. Job titles alone mislead, so we read the work history closely.

Where to find them

They come from robotics, autonomy, estimation and controls engineering. Look at teams building autonomous vehicles, mobile robots, drones, marine and agricultural machines, and defence or inspection systems. Useful titles include perception engineer, state estimation engineer, localisation engineer, SLAM engineer and robotics software engineer. Some come from research groups in robotics and have moved into product work. Others come from sensor and navigation companies.

Indicative pay

Not enough published evidence yet to give a fair range for this role, which is common for work this new. We benchmark it for you as part of a search.

Interview questions for an Autonomy Perception Engineer

  1. Describe a perception failure you traced to its cause on real hardware. How did you find it?

    Look for a specific system, a method that separated sensor, calibration, timing and algorithm causes, and evidence the fix worked. Worry if the story is vague, blames data volume, or skips the hardware.

  2. How do you decide which sensors to fuse, and at what level?

    A strong answer weighs sensor strengths, failure modes, latency, compute and the task. They should compare early and late fusion honestly. Worry about a fixed preference with no reasoning about trade-offs.

4 more questions, with what a strong answer covers, are in the Role Kit.

Job description you can post

We are building autonomous systems that work in real physical environments. We need a perception engineer to own how our machines sense, locate themselves and track what is around them. The work spans algorithms, hardware and testing, and your output will drive every decision our autonomy stack makes.

What you will do

  • Build and maintain the perception subsystem, from sensor input to fused state estimates
  • Develop detection, tracking and localisation that hold up across our operating conditions
  • Calibrate sensors and keep timing and synchronisation reliable
  • Design simulation and field tests that cover the approved operating domain
  • Measure detection and localisation error and report it clearly
  • Diagnose failures from logs and hardware runs, and fix root causes
  • Agree perception outputs and uncertainty with planning and controls colleagues

What you will bring

  • Demonstrated work on a fused perception or state estimation system running on real hardware
  • Strong grounding in sensor fusion, filtering and tracking
  • Practical computer vision experience
  • Experience with ROS or similar robotics middleware
  • Ability to quantify and communicate uncertainty
  • Evidence of testing systems in simulation and in the field
  • Clear written explanations of technical failures

Nice to have

  • Experience with SLAM or mapping
  • Work with lidar or radar pipelines
  • Experience building simulation or digital twin test environments

Free to use and adapt. If it saves you time, a link back to this page is appreciated.

Skills that matter

  • Robotics and controlAdvancedPerceive, plan and act through physical systems
  • Computer visionAdvancedAnalyse or generate visual information
  • Simulation and digital twinsWorkingBuild useful virtual representations of environments
  • Uncertainty quantificationWorkingEstimate confidence, calibration and model uncertainty

Other roles in autonomous navigation and field robotics

Hiring nowLocalisation and Mapping EngineerA Localisation and Mapping Engineer builds the system that tells a robot or vehicle where it is and what surrounds it. Without that, nothing…Hiring nowMotion Planning EngineerA motion planning engineer designs the software that decides how a robot or vehicle moves, so it reaches its goal without breaking physical limits…Hiring nowField Robotics Integration EngineerA Field Robotics Integration Engineer gets autonomy software and sensors working together on a real machine outdoors. It matters because autonomy…EmergingHumanoid Fleet TechnicianA Humanoid Fleet Technician deploys, maintains and repairs humanoid robots on customer sites. They keep the fleet working in real conditions, which…

Related roles in other families

Hiring nowRobot Learning EngineerRobot learning and manipulationA Robot Learning Engineer trains policies that let robots complete defined physical tasks reliably. The work turns a promising demo into behaviour a…Hiring nowRobot Manipulation ResearcherRobot learning and manipulationA Robot Manipulation Researcher builds the grasping and object-interaction methods that let robots handle real things reliably. They turn lab demos…EmergingVision-Language-Action ResearcherRobot learning and manipulationA Vision-Language-Action Researcher builds models that turn instructions and camera input into safe, bounded robot actions. They matter because they…Hiring nowComputer Vision EngineerComputer vision and spatial perceptionA Computer Vision Engineer builds detection and recognition systems that work in a defined setting, and proves how well they work. Companies rely on…

How we wrote this

Role definitions are our own editorial work, checked against occupational classifications, standards, research and employer pages. Titles vary by company, and this is a description of the work, not a job advert.

← Autonomous navigation and field roboticsAll new job families

Start a search

Hiring an Autonomy Perception Engineer?

Tell us the work. We find the people already doing it, whatever their job title says, and you meet them already interviewed for your role.