Senior Computer Vision Engineer

Senior Computer Vision Engineer(Aerial Threat Detection, Classification & Tracking)Location: Berlin (Onsite)About UsWe are a defense technology startup based in Berlin, building the next generation defense layer against aerial threats. Our team develops mission-critical systems that combine hardware, software, sensing, and real-time AI to operate reliably in complex real-world environments.Operating in stealth mode, we place strong emphasis on engineering rigor, real-world performance, and defense-grade system reliability.Role OverviewWe are seeking a Senior Computer Vision Engineer to design, train, deploy, and continuously improve computer vision models for aerial threat detection, classification, and tracking.This role focuses on real-world vision challenges: detecting small objects at long range, maintaining tracking stability under poor visibility and motion, classifying targets reliably, and deploying performant models on edge compute platforms such as NVIDIA Jetson / Tegra.You will own key parts of the vision model lifecycle, from dataset preparation and augmentation to model development, deployment optimization, field-data error analysis, and iterative improvement. You will work closely with robotics, tracking, and controls engineers to ensure visual perception outputs can be used reliably in real-time system behavior.This is a hands-on, production-oriented role for someone with deep experience building vision systems that work outside controlled lab conditions.This position requires onsite work in Berlin and candidates must be from a NATO member state.Key ResponsibilitiesComputer Vision Model DevelopmentDesign, train, fine-tune, and deploy computer vision models for: Long-range small-object detection, Object classification and identification, Multi-object tracking, Target state estimation supportWork with modern vision approaches, including real-time detectors, CNN-based architectures, vision transformers, tracking-by-detection pipelines, or custom modelsEvaluate trade-offs between detection accuracy, latency, robustness, and compute constraintsDevelop model pipelines that support continuous improvement from real-world field dataReal-World RobustnessImprove model performance under challenging operating conditions, including: Small targets at long range, Motion blur, Low light, glare, and changing illumination, Clouds, rain, fog, and atmospheric effects, Cluttered backgrounds, Camera movement and vibration, IR / thermal imagery artifactsAnalyze failure cases and translate them into concrete model, data, and preprocessing improvementsImprove classification confidence, tracking stability, and robustness against false positives#Dataset Lifecycle & Synthetic DataOwn key parts of the vision data pipeline, including: Data cleaning, Augmentation strategies, Label quality analysis, Error analysis, Continuous dataset improvementUse synthetic data to improve coverage of rare, difficult, or safety-critical scenariosCollaborate with simulation engineers to align synthetic data generation with real-world failure casesDefine metrics and evaluation sets for long-range detection, classification, and tracking performanceTracking & Sensor FusionDevelop and improve tracking-by-detection and multi-object tracking pipelinesIntegrate vision outputs into downstream tracking and control systemsWork with sensor inputs including: IR / thermal cameras, Laser range finder dataContribute to sensor fusion approaches where visual detections must be combined with additional measurement sourcesCollaborate with robotics, tracking, and controls engineers to ensure perception outputs are stable, timely, and actionableEdge Deployment & OptimizationDeploy and optimize models on NVIDIA Jetson / Tegra platformsOptimize inference performance using: TensorRT, CUDAEfficient preprocessing pipelinesBalance accuracy, latency, memory usage, and thermal constraintsSupport real-time perception pipelines running on embedded or edge compute hardwareRequired Qualifications6+ years of experience in computer vision, applied machine learning, or real-world perception systemsProven hands-on experience building, training, deploying, and maintaining computer vision modelsStrong experience with object detection, classification, and/or multi-object trackingExperience with real-world image data, including noisy labels, domain shift, sensor artifacts, and difficult edge casesStrong Python skills and experience with deep learning frameworks such as PyTorch or TensorFlowExperience optimizing and deploying models on edge platforms, ideally NVIDIA Jetson / TegraExperience with inference optimization tools such as TensorRT and/or CUDAStrong analytical skills for error analysis, model evaluation, and performance debuggingAbility to work closely with robotics, controls, and systems engineersOnsite availability in BerlinCitizenship of a NATO member statePreferred QualificationsBackground in defense, aerospace, robotics, autonomous systems, or industrial perceptionExperience with IR / thermal computer visionExperience with long-range small-object detectionExperience with sensor fusion involving visual detections and range measurementsExperience with synthetic data generation and simulation-driven dataset improvementExperience with tracking filters, tracking-by-detection, or real-time perception-to-control pipelinesStrong C++ skills for production integration are a plusWhat We OfferCompetitive salaryVSOP / equity participationCentral Berlin officeExtreme growth opportunity in a fast-scaling startupHoliday allowanceMonthly voucherPublic transportation subsidiesWho You AreReal-world focused: You care about models that work in the field, not just on benchmark datasetsData-driven: You analyze failures systematically and improve models through evidencePerformance-aware: You understand latency, memory, and edge deployment constraintsRobustness-oriented: You think deeply about edge cases, domain shift, and degraded conditionsCollaborative: You work effectively with robotics, tracking, and controls engineersMission-aligned: You understand the responsibility of building perception systems for defense applications