Role Overview

The MLOps Engineer – Edge AI Specialist will be a key member of Haldorix’s startup studio, responsible for translating cutting‑edge AI research into production‑ready solutions for industrial clients. This position requires deep expertise in MLOps, Edge computing, and GPU‑accelerated inference, as well as the ability to collaborate closely with hardware engineers, data scientists, and DevOps teams.

Key Responsibilities

• Design, build, and maintain end‑to‑end MLOps pipelines for Edge AI deployments on embedded GPU platforms.
• Optimize deep learning models using TensorRT, ONNX Runtime, quantization (INT8/FP16), and pruning techniques to meet performance and latency targets.
• Develop and automate CI/CD workflows with Docker, Git, Ansible, and other DevOps tools to ensure reproducible, scalable deployments.
• Orchestrate large‑scale GPU clusters across multiple industrial sites using Kubernetes/K3s, AWS IoT Greengrass, KubeEdge, and Balena.
• Monitor system health and performance with Prometheus and Grafana dashboards, and conduct GPU benchmarking and profiling.
• Ensure compliance with GDPR and data anonymization requirements for on‑prem AI systems.
• Collaborate with NVIDIA Jetson and other hardware partners to integrate cutting‑edge GPU solutions.
• Work with LLM pipelines (RAG, Pinecone, Weaviate, ChromaDB) and Stable Diffusion models for generative AI applications.
• Contribute to the development of DeVisu and Nitra3AI ventures, focusing on vision‑based optimization and generative AI for industrial performance.

Required Skills

• MLOps, Edge computing, Embedded GPU environments
• TensorRT, ONNX Runtime, Quantization (INT8/FP16), Model pruning
• Python (PyTorch, TensorFlow, FastAPI)
• DevOps tools (Docker, CI/CD, Ansible)
• Kubernetes/K3s, Networking, Linux administration
• Prometheus, Grafana, GPU performance profiling
• NVIDIA Jetson, Fleet Management Systems (AWS IoT Greengrass, KubeEdge, Balena)
• Stable Diffusion, LLM pipelines (RAG, Pinecone, Weaviate, ChromaDB)
• Industrial computer vision, IoT, Real‑time systems
• GDPR compliance, Data anonymization

Qualifications

• Master’s degree (BAC +5) in Computer Science, Engineering, or related field.
• 3–5 years of professional experience in MLOps or AI engineering.
• Fluent in English and French (native proficiency in French).
• Strong problem‑solving skills and ability to work independently in a fast‑paced startup environment.

Benefits

• Opportunity to shape the future of AI‑driven industrial solutions.
• Work on state‑of‑the‑art Edge AI systems deployed across real manufacturing sites.
• Collaborate with a multidisciplinary team of AI, hardware, and DevOps experts.
• Hands‑on experience with GPU benchmarking, inference optimization, and large‑scale orchestration.
• Competitive salary (18,000–25,000 MAD) and growth potential within a rapidly scaling startup studio.

Recruitment Process

1. Jobzyn AI interview (25–45 min).
2. Technical interview with Lead Developer or Technical Architect.
3. Practical MLOps deployment test (2–3h).
4. Final interview with the NITRA team and Haldorix partners.

Join Haldorix to accelerate high‑impact AI ventures from prototype to production, delivering tangible cost and performance breakthroughs in manufacturing AI.