Computer Vision Engineer — Aerial Perception & Target Analysis
Optimus Search · Berlin, Germany
Apply & track with Apply EdgeComputer Vision Engineer — Aerial Perception & Target Analysis
Working across IR/thermal and visible-spectrum imagery, you will design models and inference workflows that perform reliably under challenging conditions — low contrast, clutter, occlusion, and variable visibility. Your work will directly underpin system awareness, target identification, and track continuity. Onsite work in Berlin and NATO member state citizenship are mandatory.Key ResponsibilitiesDetection & Classification: Design, train, and optimise AI/ML models to detect UAS targets and classify types/behaviours from IR/thermal and visible imageryReal-Time Tracking: Integrate detection outputs into multi-target tracking pipelines, ensuring stable association, low-latency inference, and consistent identity maintenanceModel Optimisation: Adapt and compress models for edge deployment; implement inference pipelines using TensorRT, CUDA, and efficient architectures to balance accuracy and speed on NVIDIA hardwareRobustness & Adaptation: Improve performance across weather, lighting, occlusion, and sensor noise; implement data augmentation and domain adaptation to bridge simulation-to-reality gapsSensor Alignment: Work with thermal, radar, and laser teams to align imagery and detection outputs, enabling multi-sensor fusion and enhanced reliabilityEvaluation & Iteration: Build rigorous evaluation frameworks; analyse field data and failure cases; drive continuous improvement in precision, recall, false-positive suppression, and latencyDocumentation & Deployment: Maintain clear records of model architectures, training data, performance characteristics, and deployment constraintsRequired Qualifications5+ years’ experience in computer vision, deep learning, or real-time perception systemsProven track record in object detection, classification, and multi-object trackingDeep understanding of CNNs, transformer architectures, loss functions, and training methodologiesProficiency with PyTorch or TensorFlow; practical experience in model compression, pruning, and quantizationStrong Python; working knowledge of C++ for production-grade inference deploymentExperience optimising and deploying vision/AI pipelines on edge platforms — ideally NVIDIA Jetson/TegraFamiliarity with TensorRT, CUDA, and efficient inference practicesAbility to work cross-functionally with hardware, radar, and tracking engineersAvailability for onsite work in Berlin; NATO member state citizenshipDesirable CriteriaExperience with IR / thermal imagery or low-contrast, low-resolution target detectionMulti-sensor or fusion perception experience (vision + radar/RF + laser)Hands-on work with tracking-by-detection, temporal association, or re-identificationFamiliarity with operational constraints: latency, SWaP, environmental robustnessPublication or project experience in aerial perception, small-target detection, or defence-related visionIf this opportunity aligns with your expertise and professional ambitions, we would be delighted to hear from you. Please submit your application to begin the conversation.