Haldorix, a Moroccan startup studio, transforms operational challenges into scalable business opportunities through technology. The company develops ventures such as DeVisu (computer vision for operational optimization) and Nitra3AI (generative AI for industrial performance). The Lead Computer Vision Engineer will own the end‑to‑end vision system for textile production monitoring, ensuring high accuracy and real‑time performance.

Key Responsibilities:

• Lead the computer vision pipeline from acquisition to detection, tracking, and visualization.
• Perform geometric calibration to convert pixel coordinates into millimeter‑scale metrics.
• Optimize and fine‑tune the FACT‑tiny model for real‑time inference on edge or on‑premise deployments.
• Maintain system reliability, monitor mAP metrics, detect model drift, and troubleshoot live environments.
• Document FSM diagrams, model specifications, and best practices.
• Collaborate closely with lead developers and product architects to align technical design with field impact.
• Optimize GPU usage, latency, and throughput for efficient deployment.
• Mentor internal teams and transfer knowledge through clear documentation and hands‑on guidance.

Required Qualifications:

• 3+ years of hands‑on experience in computer vision (OpenCV, detection, tracking).
• Strong understanding of camera calibration and 2D/3D projective geometry.
• Proficiency in Python with scientific libraries (NumPy, OpenCV, cv2).
• Deep learning expertise for video processing.
• Experience optimizing GPUs for real‑time performance.

Nice to Have:

• Industrial automation or IoT vision system experience.
• Edge deployment and lightweight inference frameworks.
• DevOps workflows (Docker, Kubernetes, CI/CD).
• Mentoring or cross‑disciplinary collaboration experience.
• Strong documentation and communication skills in English or French.

Benefits:

• Direct impact on industrial productivity.
• Exposure to real‑world AI challenges with immediate deployment.
• Opportunity to shape and deliver a full system end‑to‑end.
• Work with a high‑impact, collaborative team.

Recruitment Process:

1. Jobzyn AI interview (25–45 min).
2. Technical interview with Lead Developer or Technical Architect.
3. Practical test based on a real‑world use case.
4. Final interview with the team and partners.