Artificial Intelligence Engineer

Discover International; Mid Sussex; Hybrid; GBP 90,000 - 110,000; Full time

Job summary

Discover International in the United Kingdom is seeking an experienced GenAI Engineer to design and build AI-powered applications on top of LLMs, delivering production-grade, scalable solutions.

You will collaborate with a cross-functional team to integrate AI into business systems, optimise prompts and costs, and implement retrieval-augmented generation with vector databases.

Qualifications

• Experience designing GenAI-powered apps on LLM platforms.
• Strong Python and backend development background.
• Knowledge of vector databases and RAG pipelines.

Responsibilities

• Design and build GenAI applications using OpenAI/Azure OpenAI and similar LLM platforms.
• Develop multi-agent solutions with agent orchestration frameworks like LangGraph.
• Create Retrieval-Augmented Generation pipelines with embeddings and vector search.
• Develop scalable Python backends and REST APIs.
• Integrate AI into existing business systems and third-party APIs.
• Optimize prompts, retrieval quality, latency and production costs.

Skills

Python

Backend development

OpenAI / Azure OpenAI

Prompt engineering

Agentic AI

API integration

LangGraph / LangChain

Vector search

Tools

Docker

Kubernetes

OpenAI API

Azure OpenAI

LangGraph

LangChain

Pinecone

Weaviate

FAISS

Milvus

OpenSearch

Job description

Location: Mid Sussex (hybrid, 3 days on-site per week)

Duration: 6 months

About the role

We're looking for an experienced GenAI Engineer to design and build AI-powered applications on top of Large Language Models and modern AI frameworks. You'll take solutions from concept through to scalable, production-grade systems, working with a cross-functional team to deliver something secure and genuinely usable at scale.

What you'll be doing

• Designing and developing GenAI applications using OpenAI / Azure OpenAI or equivalent LLM platforms
• Building multi-agent solutions with agent-orchestration frameworks such as LangGraph
• Creating Retrieval-Augmented Generation (RAG) pipelines over enterprise knowledge using embeddings and vector search
• Developing scalable Python backend services and REST APIs
• Integrating AI into existing business systems, databases and third-party APIs
• Optimising prompts, retrieval quality, latency and cost for live production workloads

What we're looking for

• Strong Python and backend development experience
• Hands-on experience with OpenAI / Azure OpenAI, prompt engineering, RAG, embeddings and vector search
• Proven experience building agentic AI with LangGraph or similar (LangChain, Semantic Kernel, AutoGen, CrewAI)
• Experience with vector databases (pgvector, Azure AI Search, Pinecone, Weaviate, Chroma, FAISS, Milvus or OpenSearch)
• Cloud (Azure / AWS / GCP), Docker and Kubernetes
• Solid grasp of API integration, tool/function calling and agent orchestration

Nice to have

• Kafka or event-driven architectures
• MLOps, LLM evaluation, observability and monitoring