Senior Computer Vision Engineer – Localization

About This Opportunity

We are representing a confidential aerospace technology client in Munich who is building the next generation of autonomous perception systems. They need a Senior Computer Vision Engineer to own the spatial state-estimation layer of their autonomy platform—the perception systems that enable unmanned platforms to understand where they are, what they see, and how to operate when GPS, lighting, timing, and real-world conditions become challenging.

This is a hands-on engineering role at the intersection of visual-inertial odometry, SLAM, sensor fusion, and real-time robotics. You'll design algorithms, write production code, analyze logs, debug sensor issues, and validate performance in simulation and live deployments. Your work will connect cameras, IMUs, GNSS, onboard compute, control systems, and spatial AI models into a coherent understanding of the world.

Responsibilities

• Build, tune, and deploy robust visual-inertial odometry and state-estimation pipelines for robotics systems operating in dynamic, outdoor, and GPS-challenged environments
• Fuse and synchronize data from cameras, IMUs, magnetometers, barometers, and other onboard sensors into reliable pose, orientation, uncertainty estimates, and spatial context
• Develop mapping, loop closure, re-localization, and map-based navigation capabilities that maintain spatial understanding across missions and degraded sensor conditions
• Own intrinsic, extrinsic, and temporal calibration workflows; diagnose drift, latency, frame drops, sync issues, rolling-shutter effects, vibration, and sensor degradation
• Optimize perception pipelines for onboard compute, including Nvidia Jetson-class platforms and resource-constrained edge systems
• Build replayable log pipelines, evaluation datasets, test metrics, and automated regression tests to measure localization accuracy, robustness, latency, and failure modes
• Analyze real mission logs, reproduce failures, isolate root causes, and improve robustness in difficult field conditions including heavy rain, snow, fog, night operations, strong vibration, and motion blur
• Define clean interfaces to planning, control, fleet coordination, operator UI, and spatial AI systems
• Mentor engineers, review architecture and code, and help define the long-term perception roadmap

What We're Looking For

• M.Sc., Ph.D., or equivalent practical background in Robotics, Computer Vision, Electrical Engineering, Computer Science, Aerospace Engineering, or related technical field
• Several years of hands-on experience building perception, SLAM, VIO, localization, sensor-fusion, or state-estimation systems for real-world robotics, AR/VR, autonomous vehicles, drones, or adjacent domains
• Strong foundations in 3D geometry, linear algebra, probability, estimation theory, optimization, filtering, and real-time robotics systems
• Production C++ skills for Linux systems and Python for analysis, evaluation, and tooling; Rust experience is a plus
• Practical experience with EKF, factor graphs, nonlinear least squares, bundle adjustment, visual odometry, inertial navigation, calibration, and multi-sensor fusion
• Experience working with real sensors and understanding that perception failures often stem from timing, calibration, vibration, lighting, motion blur, data quality, or integration issues
• Strong emphasis on metrics, logs, reproducibility, and systematic validation—you build tools to know when systems work, when they fail, and why
• Fluent English; German is a plus
• Eligibility to work on defence-related projects and obtain relevant security clearance where required

Especially valued bonus skills:

• Experience deploying perception systems on Nvidia Jetson, embedded CPUs/GPUs, writing CUDA kernels, optimizing deep neural networks for edge deployment
• Experience with LWIR thermal cameras, rolling shutter effects, visual-inertial calibration, multi-camera rigs, fisheye/wide-angle lenses, or monocular depth
• Experience with GNSS-denied navigation in UAV context, terrain-relative navigation, map-based localization and re-localization
• Experience building evaluation datasets, replay systems, perception observability, log tooling, and automated regression pipelines
• Publications or open-source contributions in SLAM, VIO, 3D computer vision, state estimation, or robotics

How We Work With You

Candidates apply directly through Get A Job.ai. Our talent team will conduct an initial screening to understand your background and ensure alignment with the role requirements. Once we confirm a strong match, we will submit your profile to our client for consideration. Please do not contact the client directly—all communication and coordination will flow through our recruiting team to ensure a professional and streamlined process.

Our client's interview process typically includes an intro call, a coding/algorithm interview focused on perception and estimation problems, a technical deep-dive into your experience with SLAM/VIO and robotics, and a final team meeting.

Pay

Pay details will be discussed during the screening process and are competitive with senior computer vision engineering roles in the Munich market.

Equal Employment Opportunity: Get A Job.ai is committed to creating an inclusive recruiting experience. We welcome applicants of all backgrounds and work to ensure fair access to opportunities regardless of race, color, religion, sex, national origin, age, disability, veteran status, or any other protected characteristic.