DevOps/SRE Engineer - GenAI/RAG/LLM Platform

Project overview

DevOps/SRE Engineer - GenAI/RAG/LLM Platform

Contract | Hybrid/Remote

We are looking for an experienced DevOps/Site Reliability Engineer (SRE) to build and operate production-grade infrastructure for Generative AI, RAG and LLM-based platforms.

This role sits at the intersection of DevOps/SRE, Kubernetes and AI engineering, with a strong focus on deploying, scaling, monitoring and supporting LLM workloads in production.

Key experience

The role

You'll help engineer the platform and operational foundations behind LLM and RAG applications, covering Kubernetes infrastructure, model deployment, vector search, observability, reliability and automated paths to production.

This would suit a DevOps/SRE Engineer who has moved into the GenAI/LLM space, rather than a traditional infrastructure engineer with no hands-on AI platform experience.

GCS is acting as an Employment Business in relation to this vacancy.

• Strong DevOps or SRE background supporting highly available production platforms.
• Hands-on Kubernetes experience, including deployment, scaling and production operations.
• Experience building or supporting RAG (Retrieval-Augmented Generation) architectures.
• Strong understanding of LLMs and production GenAI workloads.
• Vector database/search experience with Pinecone, Weaviate, pgvector or Azure AI Search.
• Experience with LangChain, LlamaIndex and/or MCP (Model Context Protocol).
• LLM observability/evaluation experience using LangSmith, Langfuse or Arize.
• Experience deploying or managing models through Hugging Face and/or AWS SageMaker.
• Strong understanding of CI/CD, infrastructure automation, monitoring, reliability and production troubleshooting.
• Ability to work closely with AI/ML and software engineering teams to take GenAI applications from development into reliable production environments.

Project details

• Start: asap
• Duration: 6 months
• Remote: hybrid
• Location: London, UK, GB
• Languages: English