Haldorix, a startup studio based in Casablanca, is dedicated to transforming operational challenges into scalable business opportunities through technology. We focus on creating industry‑specific solutions, such as DeVisu for computer vision optimization and Nitra3AI for generative AI. As a Computer Vision/Machine Learning Engineer – Inference & Model Deployment, you will play a pivotal role in building a real‑time computer vision system that monitors productivity in textile production lines.

Key Responsibilities:

• Optimization & Deployment: Export and optimize deep learning models using ONNX and TensorRT (INT8, FP16) for efficient inference on GPUs.
• Active Learning Loop: Manage data collection, annotation, and correction pipelines within CVAT to continuously improve model performance.
• Performance Benchmarking: Conduct GPU stress tests and benchmark latency, throughput, and accuracy across deployment environments.
• Validation & QA: Lead field validation sessions, perform detailed QA checks, and ensure robustness in real‑time production conditions.
• Automation & Scalability: Develop scripts and tools to streamline model conversion, quantization, and deployment workflows.
• Collaboration & Documentation: Work closely with computer vision and backend engineers to integrate optimized inference pipelines and document performance metrics.
• Continuous Improvement: Analyze bottlenecks, propose optimizations, and refine the active learning feedback loop for model accuracy.
• Testing Culture: Contribute to building a strong testing and profiling culture around ML models in production.

Qualifications:

• 2+ years of hands‑on experience in ML model deployment and inference optimization.
• Strong expertise with TensorRT, ONNX, and GPU performance optimization.
• Experience with quantization techniques (INT8, FP16).
• Proficiency in Python for scientific computing and QA/testing workflows.
• Familiarity with video annotation tools like CVAT or Label Studio.
• Proven ability to conduct GPU benchmarking and profiling.
• Strong attention to detail and commitment to production‑grade quality.
• Nice to have: experience in industrial computer vision or real‑time systems, familiarity with Active Learning workflows, auto‑annotation techniques, Docker or Kubernetes for ML model deployment, CI/CD for ML pipelines, and experience in manufacturing, logistics, or IoT environments.

Benefits:

• Join a startup studio building high‑impact industrial ventures from the ground up.
• Work on cutting‑edge real‑time computer vision systems deployed in production.
• Collaborate with a skilled, multidisciplinary team driven by innovation.
• Gain deep expertise in model optimization and production ML.

Recruitment Process:

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

Apply now to contribute to transformative industrial solutions and accelerate your career in computer vision and machine learning.