Haldorix, a forward‑thinking startup studio, specializes in transforming real‑world operational challenges into scalable technology solutions. With ventures such as DeVisu (computer vision for operational optimisation) and Nitra3AI (generative AI for industrial performance), the company thrives on innovation and measurable impact.

Position Overview

We are seeking a Computer Vision / Machine Learning Engineer – Model Training to join our Casablanca team. The role focuses on developing a real‑time productivity monitoring system for textile production lines, from data preparation to model deployment.

Key Responsibilities

• Research & Discovery: Analyse existing datasets, design optimal sampling and labeling strategies, and evaluate prior model performance.
• Design & Definition: Build and structure video training pipelines for short clips, design robust data augmentation workflows.
• Execution & Collaboration: Fine‑tune the FACT‑tiny architecture on domain‑specific data, implement GPU‑optimised training with mixed precision, monitor training via TensorBoard, manage checkpoints and retraining cycles.
• Feedback & Iteration: Conduct iterative experiments to maximise accuracy and inference efficiency, collaborate closely with engineering to integrate models into production.
• Innovation & Learning: Explore alternative architectures such as SlowFast or 3D CNNs, document findings and best practices for future deployments.

Required Qualifications

• 2+ years of experience in deep learning model training and optimisation.
• Proficiency with PyTorch and video architectures (FACT, SlowFast, 3D CNNs).
• Strong knowledge of data augmentation tools (Albumentations, imgaug).
• Experience with GPU optimisation, mixed precision, and training monitoring (TensorBoard).
• Ability to iterate quickly and improve model performance under time constraints.

Nice to Have

• Experience in industrial vision or manufacturing contexts.
• Exposure to MLOps workflows (versioning, checkpoints, pipeline reproducibility).
• Familiarity with Active Learning loops in computer vision.
• Hands‑on experience with real‑time inference pipelines or edge deployments.

Benefits

• Hybrid work model (office + remote).
• Competitive salary (14 000–22 000 MAD per month).
• Opportunity to work on cutting‑edge AI projects with real industrial impact.
• Collaborate with a small, high‑performing engineering team and startup founders.
• Freedom to experiment, learn, and push the boundaries of real‑time vision systems.

Recruitment Process

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

Company Culture

Haldorix is a startup studio that turns operational challenges into business opportunities through technology. The team values rapid iteration, cross‑disciplinary collaboration, and a data‑driven approach to product development. If you thrive in a fast‑paced environment and want to see your work directly impact production efficiency, Haldorix is the place for you.