ML Ops Engineer – Model Lifecycle & Deployment

About the role

The MLOps Engineer owns the model lifecycle across defence and strategic sector deployments, handling serving infrastructure, monitoring, evaluation pipelines, and environment management. You ensure the system is always on, accurate, and auditable.

Key responsibilities

• Design and operate model serving infrastructure for on‑premise and cloud environments.
• Build and maintain CI/CD pipelines for model updates, rollbacks, and evaluation‑gated deployments.
• Monitor production model performance—latency, accuracy drift, throughput, failure modes—and create early‑warning systems.
• Develop evaluation infrastructure including harnesses, A/B testing, and model comparison tools.
• Manage containerised model serving in constrained, air‑gapped, and edge environments.
• Collaborate with Data Scientists on evaluation pipelines and own the underlying infrastructure.
• Create runbooks and operational playbooks for Strategic Deployment Engineers in the field.
• Own incident response for model‑layer failures across all active deployments.

Required profile

• 3–5 years of ML engineering or MLOps experience with at least one production LLM or ML system.
• Deep expertise in model serving technologies such as vLLM, TGI, or Triton Inference Server.
• Experience fine‑tuning and adapting models in constrained, on‑premise, or air‑gapped environments.
• Containerisation skills with Docker, Kubernetes, or lightweight alternatives (K3s, K0s).
• Monitoring and observability using Prometheus, Grafana, or similar tools.
• Fluent Python programming and familiarity with fine‑tuning workflows.
• Hands‑on experience with CI/CD tooling for ML pipelines (GitHub Actions, ArgoCD, DVC).

Required skills

• Python
• Docker
• Kubernetes
• K3s
• K0s
• vLLM
• TGI
• Triton Inference Server
• GGUF
• AWQ
• GPTQ
• Prometheus
• Grafana
• GitHub Actions
• ArgoCD
• DVC