MLOps Engineer: Sovereign AI on Kubernetes

Dex; Greater London; In loco; GBP 85.000 - 140.000; Tempo pieno

Descrizione del lavoro

This London-based infrastructure company is seeking an experienced MLOps engineer to own deployment, observability, and reliability of LLM services on high-throughput Kubernetes infrastructure. You will work at the intersection of distributed systems, GPU scheduling, and agent execution logic to deliver scalable AI platforms for enterprise clients.

You will define deployment patterns, orchestration strategies, and cost optimizations while maintaining traceability and resilience under real-world

Competenze

• 3+ years in MLOps/LLMOps or AI platform engineering with production Kubernetes workloads.
• Strong Python engineering with Infrastructure as Code and modern CI/CD automation.
• Hands-on observability and LLM tracing using OpenTelemetry, Prometheus, Grafana, LangSmith, Langfuse, or Arize.
• Experience with agentic architectures, including state persistence and multi-step agent failure handling.

Mansioni

• Architect and automate zero-downtime deployment pipelines for LLM services and autonomous agent workflows on Kubernetes, using canary and blue/green rollouts.
• Build end-to-end evaluation and observability framework to trace non-deterministic agent paths, monitor hallucination rates, and detect model drift.
• Own GPU and CPU allocation, cluster autoscaling and compute efficiency to drive down time-to-first-token while controlling infrastructure expenditure.
• Maintain the stability and latency of critical data subsystems, including real-time vector indexing, embedding pipelines, and feature stores.
• Diagnose complex production failure modes that span agent runtime logic, orchestration frameworks, and underlying cloud infrastructure.

Conoscenze

MLOps

LLMOps

Kubernetes

Python

CI/CD

Strumenti

OpenTelemetry

Prometheus

Grafana

LangSmith

Langfuse

Arize

Descrizione del lavoro

This London-based infrastructure company is seeking an experienced MLOps engineer to own deployment, observability, and reliability of LLM services on high-throughput Kubernetes infrastructure. You will work at the intersection of distributed systems, GPU scheduling, and agent execution logic to deliver scalable AI platforms for enterprise clients.

You will define deployment patterns, orchestration strategies, and cost optimizations while maintaining traceability and resilience under real-world