Senior MLOps Engineer (OpenShift / AI Platform)

About the role

OBSS, an engineering-led technology consultancy, is looking for a Senior MLOps Engineer to architect, scale and maintain its enterprise-grade machine learning infrastructure. The role bridges data science and core infrastructure, building reliable pipelines across a hybrid ecosystem of on-premises OpenShift multi-GPU environments and major global cloud providers.

Key responsibilities

• Manage and scale production ML workloads across containerized systems, specializing in Red Hat OpenShift on-premises and managed Kubernetes (EKS, AKS, GKE, CCE)
• Optimize on-premises NVIDIA multi-GPU clusters by configuring, monitoring and partitioning resources with CUDA, TensorRT and MIG profiles
• Deploy and monitor models across AWS SageMaker, Azure ML, GCP Vertex AI and Huawei Cloud (ModelArts)
• Build fully automated ML pipelines covering CI, CD and CT with MLflow, Kubeflow, Argo Workflows or GitLab CI
• Set up runtime environments for batch and real-time inference with Triton, vLLM, KServe or FastAPI
• Implement logging, tracing and metrics with Prometheus, Grafana and OpenTelemetry to track data drift and model decay

Required profile

• 3-6 years of experience in MLOps, ML platform engineering or DevOps supporting heavy-compute workloads
• Hands-on experience with Red Hat OpenShift and NVIDIA hardware/software stacks (CUDA, drivers, driver operator)
• Proven deployment of architectures across AWS, Azure or GCP, plus familiarity with Huawei Cloud; Ascend NPU integration is a big plus
• Nice to have: Huawei Ascend NPU knowledge, LLMOps and fine-tuning frameworks (DeepSpeed, Megatron-LM), and Red Hat OpenShift or multi-cloud professional certifications

Required skills

• Terraform, Ansible or Pulumi for immutable infrastructure
• Expert-level Python and strong Linux shell scripting
• Familiarity with feature stores, DVC or vector databases for GenAI deployments