Direct message the job poster from Norconsult Telematics

• Design and operationalize scalable MLOps workflows to support deployment and lifecycle management of traditional ML, LLMs, RAG pipelines, and agentic AI systems across production environments.
• Build CI/CD and GitOps pipelines, model serving infrastructure (e.g., Triton, ModelMesh), and ensure observability, performance monitoring, and traceability to enable reliable and efficient AI delivery.

Job Description & Responsibilities:

• Develop and manage end-to-end CI/CD pipelines for AI/ML workloads using tools like Kubeflow, Tekton, or Argo Workflows.
• Implement GitOps workflows for reproducible, version-controlled model deployments.
• Integrate and manage LLM and GenAI model serving using platforms such as Triton, ModelMesh, ONNX, or OpenVINO.
• Monitor model drift, latency, resource usage, and enable automated alerts or rollbacks.
• Collaborate with Data Science, AI, and Infrastructure teams to define scalable compute and storage needs.
• Ensure model traceability, audit readiness, and performance tracking across environments.
• Support production-grade agentic workflows and multi-step LLM inference pipelines.
• Apply strong communication and documentation skills to explain model workflows and infrastructure clearly.
• Demonstrate adaptability and problem-solving to debug complex AI pipelines and implement scalable solutions.
• Work collaboratively across cross-functional teams, manage time effectively, and deliver on fast-paced deadlines.

Qualification & Experience:

• Bachelor's degree in Computer Science, Software Engineering, or related field with 4+ years' experience in MLOps, DevOps, or AI platform engineering.
• Proficient in OpenShift, Kubernetes, and GPU orchestration for scalable AI workloads.
• Hands on experience with LLM model serving, containerized AI (Docker, Triton, ONNX), and observability tools like Prometheus and Grafana.
• Familiarity with MLflow, ModelMesh, Seldon, KServe, and supporting GenAI/LLM pipelines, RAG, and agentic frameworks (preferred).
• Certified in Kubernetes (CKA), OpenShift, or major cloud platforms (AWS, Azure, GCP) is advantageous.
• KPIs include pipeline uptime/failure rate, time to deploy models, and model latency/availability.
• Fluency in English is mandatory; Arabic proficiency is a plus.

Seniority level

Mid-Senior level

Employment type

Contract

Job function

Information Services and Data Infrastructure and Analytics