LLM Engineer

Adria Solutions Ltd; England; On-site; GBP 60,000 - 80,000; Full time

Job summary

A leading technology consultancy in the United Kingdom is looking for an experienced LLM Engineer/AI Engineer to design and deploy LLM-driven features. The ideal candidate will possess strong Python skills and experience in the deployment of LLMs in production. They will work collaboratively in a fast-paced environment, tackling meaningful, complex challenges. This position offers the chance to shape LLM usage in production and ensure compliance with standards.

Qualifications

• Proven experience deploying LLMs in production.
• Strong Python development skills.
• Hands-on experience with RAG and embeddings.

Responsibilities

• Design, build and deploy LLM-driven features
• Collaborate with teams to deliver high-value use cases
• Ensure solutions meet security and compliance standards.

Skills

LLM deployment experience

Python development

Prompt engineering

Retrieval-Augmented Generation (RAG)

Embeddings and vector databases

FastAPI / Flask

Tools

Docker

Linux

Job description

The Role

You will:

• Design, build and deploy LLM-driven features into live products and platforms
• Work with both commercial and open-source LLMs, selecting the right model for each use case
• Build and optimise RAG pipelines, embeddings and vector-based retrieval solutions
• Develop APIs and services that integrate LLMs with existing AI, data and platform systems
• Optimise solutions for performance, reliability, latency and cost
• Collaborate with engineering, AI and product teams to identify and deliver high-value use cases
• Ensure all solutions meet security, compliance and data governance standards

What My Client Is Looking For

Essential

• Proven experience deploying LLMs in production
• Strong Python development skills
• Hands‑on experience with:
• Prompt engineering and evaluation
• Retrieval‑Augmented Generation (RAG)
• Embeddings and vector databases (e.g. FAISS, Pinecone, Weaviate, Chroma)
• Experience building LLM‑backed services using FastAPI / Flask or similar
• Strong understanding of trade‑offs around accuracy, latency, cost and scalability

Highly Desirable

• Experience working with or fine‑tuning open‑source LLMs
• Familiarity with LLMOps (monitoring, evaluation, guardrails, versioning)
• Experience integrating LLMs into complex or data‑heavy systems
• Docker and Linux experience
• Background in regulated, industrial or safety‑critical environments

The Right Mindset

• Pragmatic, delivery‑focused and comfortable working with ambiguity
• Able to translate complex AI concepts into practical solutions
• Confident owning problems end‑to‑end, from idea through to deployment
• Motivated by building AI that has real‑world impact

Why Apply?

• High‑impact role with real ownership
• Opportunity to shape how LLMs are used in production environments
• Work on meaningful, technically challenging problems
• Collaborative engineering culture within a scaling business

Interested? Please Click Apply Now! LLM Engineer / AI Engineer Cheshire