Computer Vision Engineer - Body Sensor Networks

Xsens

WorldwideremotePosted 8 days ago

Skill Required

Computer-Vision-EngineerPerception-EngineerMachine-Learning-EngineerComputer-Vision-Software-EngineerComputer-Vision-ResearcherComputer-Vision-ML-EngineerComputer-Vision-and-Machine-Learning-EngineerVision-Systems-EngineerComputer-Vision-EngineeringPerception-Systems-EngineerComputer Vision EngineerComputer VisionDeep Learningrelated fieldEngineeringautomationdevelopingData StructuresanalyticsbuildingPythonC++Design PatternsandFulltime

Key highlights

Competitive compensation package
MSc/PhD in Computer Science, Electrical Engineering, Robotics or a related field, with years of relevant industry or applied research experience
28 paid vacation days with an option to buy, sell, or carry over days

Role overview

As a Computer Vision Engineer at Xsens, you will lead camera-based perception for Xsens motion capture, establishing Deep Learning and Computer Vision pipelines to turn camera images into human pose estimates. You will learn from a highly-skilled team of sensor fusion experts, biomechanists, and mathematicians as its computer vision specialist, reporting to the Technology Manager.

Responsibilities

Select, adapt and fine-tune deep learning models for 2D and 3D human pose estimation from cameras, that perform robustly in challenging real-world conditions.
Develop camera models and calibration routines for a range of camera and lens configurations.
Evaluation of motion capture output and developing compensatory algorithms and techniques to handle camera /vision failure modes.
Build training and evaluation pipelines from camera and optical motion capture recordings. Use synthetic data where real data is insufficient.
Track the computer vision research landscape and assess whether new techniques are feasible for Xsens products.

Requirements

Xsens is looking for a hands-on Computer Vision Engineer who combines strong theoretical foundations with a proven ability to build and ship working systems.
MSc/PhD in Computer Science, Electrical Engineering, Robotics or a related field, with years of relevant industry or applied research experience.
Hands-on experience training and fine-tuning deep learning models for human pose estimation, with results evaluated on public benchmarks.
Solid understanding of camera and lens models, including wide field-of-view optics, intrinsic and extrinsic calibration, and multi-view geometry.
Familiarity with the output representations of common pose models, such as keypoint sets and SMPL-family parameters.
Experience with tools in markerless eco-system such as OpenCV, Sapiens, and SAM3D.
Proficiency in Python. Working knowledge of C++ for integrating models into an existing C++ codebase.

Nice to have

Experience with synthetic data generation and rendering pipelines.
Experience optimizing models for real-time deployment, for example with ONNX, TensorRT or quantization.
Experience building datasets and benchmarks for human motion.

Benefits

Competitive compensation package
28 paid vacation days with an option to buy, sell, or carry over days, giving you flexibility to manage your time off as appropriate to your situation
Tax perks for your sports memberships and bicycle purchase; so staying active is easier than ever.
Flexible working hours and the option to work from home, helping you balance life and work
Paid volunteer time: Through our partnership with Stichting Present, you have the opportunity to give back to the community during office hours
Our partnership with Equip gives you on-demand access to a dedicated financial planner who provides clear guidance and a concrete plan for wealth building, pensions, and major life events.
Enjoy company social events as well as fun, informal activities organized by our staff association. From movie nights and sports clinics to cooking classes and LAN parties, there’s always something happening to connect and have fun