Computer Vision Engineer

Job description

Do you get excited about building cutting-edge perception systems that work reliably in the real world? Do you have a strong foundation in computer vision, robotics, or sensor fusion? Are you interested in shaping new technology capabilities within a growing and innovative high-tech company, where people and fun are part of our core values? We’d love to have you!

Xsens is a leading full-stack provider of sensors, software, and analytics that enable the digitization of movement. Xsens serves entertainment, humanoid robotics, health & sports and automation & mobility markets. By turning complex motion data into actionable insight, we help our partners accelerate development, improve control and learning, and bring physically intelligent systems to life. We collaborate with leading global innovators including Boston Dynamics, Toyota, Siemens, Electronic Arts, Epic Games, Netflix, and 20th Century Studios, alongside more than 1,000 research institutions, humanoid robotics companies and universities worldwide.

As a Computer Vision Engineer, you play a key role in expanding Xsens’ core technology by introducing and maturing vision as a complementary sensing modality alongside our inertial systems.

Imaging is a relatively new domain within Xsens. You will help build in-house expertise in vision-based perception, focusing on integrating camera data with IMU-based systems for applications such as markerless human motion capture and dead-reckoning in GNSS-denied environments.

You will work on 6-DoF pose estimation and multi-sensor fusion, developing systems that improve robustness, accuracy, and drift performance in real-world conditions. You contribute not only by implementing solutions, but also by shaping how vision becomes a core capability within Xsens.

We actively leverage Generative AI tools to accelerate development and improve quality. You are expected to embrace these tools as part of your workflow and continuously explore how they can enhance development, experimentation, and performance.

You will be based in Enschede, the Netherlands, and work closely with our multidisciplinary engineering teams.

• Design and implement Visual-Inertial Odometry (VIO) and SLAM pipelines
• Develop vision-based approaches for markerless human motion capture and tracking
• Develop and maintain camera models, calibration routines, and sensor synchronization across hardware setups
• Apply state estimation, optimization, and filtering techniques for accurate 6-DoF pose estimation
• Own and improve end-to-end perception pipelines, from sensor integration to system validation
• Ensure robustness and performance in dynamic, uncontrolled environments
• Translate state-of-the-art research into production-ready solutions
• Collaborate closely with hardware, firmware, and software teams to deliver integrated systems

We are looking for a hands-on and proactive Computer Vision Engineer who thrives in an environment where new capabilities are being built and ownership is key. You are comfortable working across theory and implementation, and you can turn complex concepts into robust, real-world systems. You have:

• MSc or PhD in Computer Science, Electrical Engineering, Robotics, or a related field
• Proven experience building real-time or performance-constrained systems
• Strong programming skills in C++ and/or Python
• Hands-on experience with VO, VIO, SLAM, or related perception systems
• Solid understanding of multi-view geometry, camera models, and calibration
• Strong mathematical foundation in linear algebra, probability, and state estimation
• Experience working with multi-sensor systems (e.g., IMU + vision)
• Strong analytical and problem-solving skills, including debugging across system layers
• Excellent English communication skills and a collaborative mindset
• Self-motivated with the ability to take ownership and work independently

You take ownership and build new capabilities, not just components

• You are curious and driven to explore new sensing modalities and approaches
• You think in terms of systems and real-world performance, not just…