Python AI Engineer

Stott and May Inc.; Coventry; Hybrid; GBP 70,000 - 110,000; Full time

Job summary

Stott and May Inc. is seeking an experienced Python AI Engineer to build and productionise Generative AI and RAG solutions, spanning AI orchestration, retrieval, evidence processing, LLM integration, and response validation.

You will collaborate with engineering, data and platform teams to deliver production-grade services and robust AI workflows with tool calling and structured outputs. This hybrid role is based in central London with an ASAP start.

Qualifications

• Strong commercial Python development experience, including async programming and testing.

Responsibilities

• Build and maintain production-grade Python AI/RAG services.
• Develop multi-step AI workflows with tool calling and schema validation.
• Implement vector, lexical and hybrid retrieval and evidence selection.
• Develop automated tests and monitoring for AI systems.
• Improve AI quality, latency and reliability through production feedback.

Skills

Python

Async programming

Typing

Testing

Performance optimization

LLM integration

Tool calling

RAG workflows

Embeddings

Vector search

Tools

Pydantic

LangGraph

Semantic Kernel

Docker

Pytest

Git

CI/CD

Azure OpenAI

Kubernetes

Telemetry

Job description

Python AI Engineer

Start: ASAP

Duration: 6 months +

Location: hybrid, central London

Rate: DoE, inside IR35

We’re looking for an experienced Python AI Engineer to build and productionise Generative AI and RAG solutions. You’ll work across AI orchestration, retrieval, evidence processing, LLM integration, response generation and validation, collaborating with engineering, data and platform teams.

Key Responsibilities

• Build and maintain production-grade Python AI/RAG services.
• Develop multi-step and agentic AI workflows using structured outputs, tool calling and schema validation.
• Implement vector, lexical and hybrid retrieval, reranking, metadata filtering and evidence selection.
• Build robust asynchronous services with appropriate retries, timeouts and failure handling.
• Develop automated unit, integration, contract and regression tests.
• Implement logging, tracing, monitoring and performance optimisation.
• Improve AI quality, latency, cost, token usage and reliability through evaluation and production feedback.

Essential Experience

• Strong commercial Python development experience, including async programming, typing, testing and performance optimisation.
• Proven delivery of Generative AI and RAG solutions into production.
• Hands‑on experience with Pydantic, LangGraph, Semantic Kernel / Microsoft Agent Framework or similar.
• Strong understanding of LLM integration, structured outputs, tool calling, prompt/model management and fallback strategies.
• Strong knowledge of embeddings, vector/lexical search, hybrid retrieval, query decomposition, chunking and reranking.
• Experience with Pytest, APIs, Git, CI/CD, Docker and observability.
• Strong troubleshooting skills across application, retrieval, model, concurrency and performance issues.

Desirable

• Azure OpenAI / Azure AI Search / Azure AI Foundry
• Pydantic AI, LangGraph or Semantic Kernel
• RAG/LLM evaluation and retrieval-quality metrics
• Kubernetes, telemetry and load testing
• Knowledge graphs, temporal retrieval or document linkage
• AI monitoring, governance and prompt-injection protection
• Experience working in regulated or specialist knowledge domains