AI​/ML​/DevOps Engineer

What you ll own

• End‑to‑end MLOps/LLMOps reference architecture: ingestion, validation, feature & embedding pipelines, training & fine‑tuning, evaluation, registry, deployment & monitoring (including RAG and agentic workflows)
• Architect, review and approve CI/CD for ML and LLM systems covering code, data, prompt and model artifact versioning; build and release pipelines in Azure Dev Ops and Git Hub Actions; automated unit, integration, contract testing and promotion/rollback with blue‑green, canary across dev, test and production
• Define and govern AI platform foundations on Azure using IaC (Bicep, Terraform); set up AML work spaces, AKS GPU node pools, private networking, VNet integration, Private Link, identity, Managed Identities, PIM, secrets, Key Vault, encryption and data residency controls
• Review and approve production deployment patterns for model and LLM serving (AKS, KServe, AML online endpoints); oversee containerization, inference optimisation, batching, quantisation, API management, autoscaling, resiliency, RAG runtime components, vector store, retriever, re‑ranker, cache
• Own observability and reliability for AI services:
  Open Telemetry tracing, prompt and inference logs with PII controls, latency, throughput, cost metrics, SLOs/SLIs, model performance monitoring, data and model drift detection, LLM evaluation for quality, hallucination checks, toxicity and safety guardrails, incident playbooks
• Establish and enforce MLOps/LLMOps governance: dataset lineage, data quality validation, schema and tests, feature store and model registry standards, artifact provenance, SBOM/SLSA, vulnerability scanning, approval gates for model and prompt releases, compliance‑aligned documentation for model risk, intended use limitations, evaluation results
• Enable delivery squads, including the primary delivery partner, with golden path templates (AML pipelines, RAG blueprints, evaluation harnesses, reusable IaC modules, coding standards); run deep technical design and architecture reviews; sign off on production readiness, capacity, security, observability, DR for all AI releases
• Support the Run & Operate model: issue triage and minor enhancement workflows, ticket intake, fix, controlled release; ensure changes follow release governance and quality gates
• Own the Operational Acceptance Gate: no production release without runbooks, monitoring dashboards, incident playbooks, access to model and DR test evidence; provide platform standards, review and sign‑off without replacing the delivery partner’s engineering while enforcing the golden path and production readiness bar

• 8–10 years across Dev Ops, SRE and/or ML Engineering with production systems on Azure
• Hands‑on experience with Azure ML, AKS, Azure Dev Ops or Git Hub Actions, IaC and containerisation
• Bachelor's in Computer Science, Engineering or equivalent experience

• Python, YAML, Docker, Helm, KQL, Git Ops, Argo Flux awareness
• Security in CI/CD, SAST, DAST, supply‑chain security (Sigstore), secrets management, Key Vault
• Performance testing (k6, JMeter), contract testing and end‑to‑end testing
• Cost optimisation and capacity planning for GPU and CPU workloads
• Strong grasp of model serving, inference optimisation and observability tooling

• Microsoft Certified:
  Dev Ops Engineer Expert (AZ‑400)

• Microsoft Certified:
  Azure Administrator (AZ‑104) or Solutions Architect (AZ‑305)
• CKA or CKAD (Kubernetes)