Join Haldorix, a startup studio turning real-world operational challenges into scalable business opportunities through technology. We identify recurring problems in industries such as manufacturing, retail, and logistics, and transform them into ventures with measurable impact. We’re looking for a Lead Computer Vision Engineer to own the video-processing and calibration pipeline of a real-time industrial vision system for textile production monitoring. This is an intensive mission to deliver a fully functional and production-ready system, ideal for a seasoned engineer who thrives under pressure and in fast-moving environments.

- Lead Computer Vision Pipeline: Oversee the full video-processing chain from acquisition to detection, tracking, and visualization. - Geometric Calibration: Compute homographies to transform pixel coordinates into millimeter-scale real-world metrics. - Model Optimization: Manage and fine-tune FACT-tiny for high performance and robustness in real-time inference. - System Reliability: Ensure consistent mAP metrics, monitor model drift, and troubleshoot in live environments. - Documentation: Maintain structured FSM (Finite State Machine) diagrams and model specifications. - Cross-Functional Collaboration: Work closely with the lead developer and product architect to align system components. - Performance Tuning: Optimize GPU usage, latency, and throughput for on-edge or on-premise deployments. - Knowledge Transfer: Support internal teams through clear documentation and hands-on mentorship.

You’ll work within a small high-impact team composed of talented engineer. Collaboration is fast, pragmatic, and outcome-driven. You’ll collaborate with the Lead Developer and Lead architect to ensure that technical design aligns with measurable field impact. The environment is dynamic, collaborative, and experimentation-friendly, exactly where applied research meets operational excellence.

Required - 3+ years of hands-on experience in Computer Vision (OpenCV, detection, tracking). - Understanding of camera calibration and 2D/3D projective geometry. - Proficiency in Python with scientific and vision libraries (NumPy, OpenCV, cv2). - Strong understanding of Deep Learning architectures for video processing. - Experience optimizing GPUs for real-time performance. Nice to Have - Prior work in industrial automation, or IoT vision systems. - Familiarity with edge deployment and lightweight inference frameworks. - Knowledge of DevOps workflows (Docker, Kubernetes, CI/CD). - Experience mentoring or collaborating with multi-disciplinary teams. - Strong documentation and communication skills in English or French.

- Direct, measurable impact on industrial productivity. - Exposure to real-world AI challenges with immediate operational deployment. - Opportunity to shape and deliver a full system end-to-end. - Work alongside a team of experts combining AI, software, and industry know-how.