Salary: £? – ? per year
Requirements:
- We require hands‑on experience building and deploying production LLM applications.
- We require strong experience with RAG, including document ingestion, chunking strategies, embeddings, vector search and retrieval, context engineering, and prompt orchestration.
- We require LLM deployment experience, not just experimentation.
- We require experience with Azure OpenAI, Ollama and/or Vertex AI.
- We require strong Python, FastAPI, and REST API development skills.
- We require experience with LangChain and/or LangGraph.
- We require experience with AKS, Kubernetes, Docker, and Helm.
- We require secure AI development and DevSecOps experience, including RBAC, Azure AD, Key Vault, secrets management, secure deployment patterns, auditability, and governance.
- We require experience with LLM evaluation and optimisation, including grounding, hallucination detection, response quality measurement, accuracy testing, and prompt and context engineering.
- We require the ability to explain RAG end to end, embeddings and vector databases, production LLM operations, AI security, model performance evaluation, and exposing AI capabilities through APIs and enterprise applications.
- We prefer experience with Azure AI Foundry, agentic AI, MCP, private LLM deployments, and enterprise security in regulated environments.
Responsibilities:
- We build, deploy, and secure production‑grade AI applications within a regulated enterprise environment.
- We deliver real‑world GenAI solutions rather than research or proof‑of‑concept work.
- We explain both the concepts and implementation behind our GenAI solutions.
- We design and implement end‑to‑end RAG solutions.
- We deploy and operate LLMs in production.
- We secure AI systems and protect sensitive data.
- We evaluate and improve model performance.
- We expose AI capabilities through APIs and enterprise applications.
Technologies:
- AI
- API
- Azure
- DevSecOps
- Docker
- FastAPI
- Helm
- Kubernetes
- LLM
- Python
- REST
- RBAC
- Security
- Cloud
More:
We are hiring a Senior Generative AI Engineer / AI Software Engineer for a 6-month contract with potential to extend. We are looking for a hands‑on engineer who can build, deploy, and secure production‑grade AI applications in a regulated enterprise environment. This role is focused on real‑world delivery, and we want someone who has already built, deployed, secured, and evaluated GenAI solutions in production and can clearly explain the architecture and decisions behind them. Desirable experience includes Azure AI Foundry, agentic AI, MCP, private LLM deployments, and working in enterprise security and regulated environments. Candidates with primarily notebook‑based, research, or experimentation experience are not suited to this role.
last updated 27 week of 2026
#J-18808-Ljbffr…