Senior Python AI Engineer: GenAI & RAG Production

Deloitte (UK); Greater London; On-site; GBP 90,000 - 130,000; Full time

Job summary

Deloitte UK is seeking a hands-on software engineer to develop production-grade Python services for Generative AI and RAG solutions. You will design modular services, define API contracts and integrate LLMs, working with engineering, data and evaluation specialists to translate research into reliable production systems.

The role emphasises performance, testing and tracing, with duties spanning multi-stage retrieval, structured logging, and operational monitoring.

Qualifications

• Production-grade Python applications and services experience.
• Asynchronous programming, type annotations, modular design, exception handling, performance optimization.
• Experience with Generative AI orchestration frameworks (Pydantic, LangGraph, Semantic Kernel).
• Experience delivering Generative AI and RAG solutions beyond POC stage.
• Knowledge of embeddings, vector/graph/lexical search, retrieval and evidence selection.

Responsibilities

• Design, develop and maintain production-grade Python services for Generative AI and complex RAG solutions.
• Define typed application, API and model contracts.
• Integrate LLMs using structured outputs, tool calling, schema validation, context management and controlled fallback mechanisms.
• Implement multi-stage retrieval using vector search, lexical search, hybrid retrieval, metadata filtering, reranking and evidence selection.
• Build asynchronous services with appropriate timeout, retry, cancellation and exception-handling controls.
• Develop automated unit, integration, contract, regression and failure-path tests.
• Implement structured logging, tracing and operational metrics across AI workflows.
• Monitor and optimise response quality, latency, token usage, cost, concurrency and memory utilisation.
• Translate evaluation findings and production issues into measurable improvements and regression tests.
• Contribute to technical design, code reviews, engineering standards and production support.

Skills

Python programming

Async programming

Generative AI

RAG systems

APIs and services

Testing with Pytest

Docker

Kubernetes

Azure OpenAI

LangGraph/Semantic Kernel

Tools

Docker

Kubernetes

Git

CI/CD

Azure OpenAI

Job description

Deloitte UK is seeking a hands-on software engineer to develop production-grade Python services for Generative AI and RAG solutions. You will design modular services, define API contracts and integrate LLMs, working with engineering, data and evaluation specialists to translate research into reliable production systems.

The role emphasises performance, testing and tracing, with duties spanning multi-stage retrieval, structured logging, and operational monitoring.