Job
- Level
- Experienced
- Job Field
- Data, Embedded
- Employment Type
- Full Time
- Contract Type
- Permanent employment
- Location
- Gilching
- Working Model
- Onsite
Job Summary
In this role, you will develop high-performance camera pipelines for autonomous object detection and tracking, and optimize algorithms for integrated sensor fusion and GPS-denied navigation.
Job Technologies
Your role in the team
- At Quantum Systems, we are building highly autonomous interceptor systems that must perceive, decide, and act under extreme latency, motion, and environmental constraints.
- We are looking for a Computer Vision & AI Engineer to drive the perception stack of our Counter-UAS interceptor platform.
- You will work on low-latency camera pipelines, small-object detection, object tracking, sensor fusion, visual odometry, precision landing, camera calibration, embedded inference, and data pipelines for training and validation.
- You will develop the vision and AI pipeline that turns raw camera data into actionable perception outputs for autonomous flight.
- This includes low-latency detection and tracking, motion-aware vision, sensor fusion with inertial data, 3D direction-vector estimation, GPS-denied navigation, and precision landing support.
- Bring up, optimize, and maintain high-performance camera pipelines, including CSI camera interfaces, raw image access, buffering, synchronization, and latency reduction.
- Develop detection algorithms for small and difficult-to-see objects in moving and rotating camera images.
- Combine machine learning and classical computer vision approaches where appropriate.
- Fuse inertial data, motion information, and visual data to improve detection and tracking in moving image sequences.
- Build object tracking pipelines that can switch from initial detection to low-latency tracking once a target has been acquired.
- Optimize perception pipelines for embedded execution on NVIDIA Jetson platforms.
- Work toward high frame-rate processing targets in the range of 100-300 FPS, where technically feasible.
- Use camera intrinsics and extrinsics to transform image-space detections into 3D direction vectors or other navigation-relevant outputs.
- Work on GPS-denied navigation concepts using visual odometry, including approaches with forward-facing camera views rather than only downward-looking cameras.
- Develop visual support for precision landing, including height estimation, velocity estimation, and motion-state estimation from limited camera perspectives.
- Build and maintain the data pipeline from onboard recordings to cloud storage, preprocessing, annotation, dataset generation, training, validation, and benchmarking.
- Work with annotation tools such as SuperAnnotate, CVAT, Label Studio, or comparable systems.
- Benchmark and evaluate different model and algorithm families, including approaches such as CenterNet, SuperPoint, SuperGlue, optical flow, feature tracking, object detection, and lightweight embedded models.
- Build deployment pipelines using ONNX, TensorRT, custom inference runners, or comparable embedded inference tooling.
- Collaborate closely with autonomy, flight control, embedded software, test, and systems engineering teams.
This text has been machine translated. Show original
Our expectations of you
Education
- Master's degree or PhD in computer vision, AI, robotics, machine learning, electrical engineering, computer science, aerospace engineering, or a comparable technical field.
Qualifications
- Strong understanding of computer vision fundamentals, camera geometry, feature detection, object detection, tracking, calibration, and image-space to 3D transformations.
- Ability to read, understand, and implement ideas from current research papers.
- Understanding of latency, throughput, profiling, memory movement, and real-time constraints.
- Strong mathematical intuition and willingness to debug both algorithms and real-world sensor data.
- Ability to take ownership of a technical area and drive it from research prototype to flight-test-ready software.
- Publications, thesis work, GitHub projects, demos, or competition results in computer vision, robotics, AI, or autonomous systems.
Experience
- Practical experience implementing computer vision or machine learning pipelines in Python and C++.
- Experience with embedded inference, ideally on NVIDIA Jetson, CUDA, TensorRT, ONNX, GStreamer, V4L2, or similar technologies.
- Experience with dataset creation, annotation workflows, training/validation splits, metrics, and benchmarking.
- Experience with UAV perception, robotics perception, visual odometry, SLAM, sensor fusion, or tracking systems.
- Experience with IMU-camera fusion, ego-motion compensation, rolling-shutter effects, or high-frame-rate cameras.
- Experience with precision landing, visual navigation, or GPS-denied navigation.
- Experience building cloud-based ML training and validation pipelines.
This text has been machine translated. Show original
What we offer
- Be at the forefront of next-generation Defence innovation.
- Work in a fast-paced, agile environment where your ideas make an impact.
- Collaborate with a team of industry pioneers who are ambitious, bold, and visionary.
- Opportunities for individual and professional growth in a globally recognized organization.
This text has been machine translated. Show original
Benefits
Work-Life-Integration
Topics that you deal with on the job
Job Locations
This is your employer
Quantum-systems Gmbh
Quantum-Systems GmbH began focusing on the development and production of autonomous transition aircraft for civilian purposes in January 2015. This was a smart move that has positioned the company as a leader in this growing industry. Autonomous transition aircraft are an important part of the future of aviation, and Quantum-Systems GmbH is at the forefront of this exciting new technology.
Description
- Company Size
- 50-249 Employees
- Language
- English
- Company Type
- Established Company
- Working Model
- Hybrid, Onsite
- Industry
- Industry, Production, Aviation, Space Travel
Computer Vision & AI Engineer
- Location
- Gilching
- Working Model
- Onsite
- Diversity
- Open for all genders
- English Only
- English only required
