> Markdown version of [/jobs/ext/3254317-contract-python-ai-engineer](https://www.wearedevelopers.com/jobs/ext/3254317-contract-python-ai-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Contract - Python AI Engineer - **Company:** Deloitte - **Location:** London, UK - **Contract:** Temporary contract - **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Automation of Tests, Microsoft Azure, Profiling, Code Review, Continuous Integration, Serialization, Memory Management, Graph Database, Information Retrieval, Python (Programming Language), Load Testing, Modular Design, Performance Tuning, Regression Testing, Search Technologies, Software Engineering, Enterprise Search, Data Logging, Retrieval-Augmented Generation, Large Language Models, Concurrency, Generative AI, Git, Fastapi, Pytest, Kubernetes, Asynchronous Programming, Software Version Control, Dynatrace, Automation Anywhere, Docker - **Published:** September 30, 2026 - **Apply:** https://apply.deloitte.co.uk/UKCareers/Login?jobId=25315 ## About the Role * Strong commercial experience developing production-grade Python applications and services. * Advanced Python skills, including asynchronous programming, type annotations, modular design, exception handling, profiling and performance optimisation. * Strong hands-on experience with Generative AI orchestration frameworks (Pydantic, LangGraph, MS Agent Framework/Semantic Kernel) including typed models, nested schemas, custom validation, serialisation and schema-constrained LLM outputs. * Demonstrable experience delivering Generative AI and RAG solutions beyond the proof-of-concept stage. * Strong understanding of embeddings, vector, graph and lexical search, hybrid retrieval, query decomposition, chunking, metadata filtering, reranking and evidence selection. * Experience integrating LLMs using structured outputs, function or tool calling, prompt and model versioning, token management, response validation and fallback strategies. * Experience building multi-step, agentic or workflow-based AI applications. * Strong automated testing experience using Pytest or equivalent frameworks. * Experience with APIs, distributed services, Git, CI/CD, containers and production observability. * Experience implementing structured logging, distributed tracing and operational monitoring. * Strong troubleshooting skills across application behaviour, retrieval quality, model execution, concurrency, memory usage and performance. Technical Skillsets * Experience with Azure OpenAI, Azure AI Search or equivalent AI and enterprise search platforms. * Familiarity with Pydantic AI, LangGraph, Semantic Kernel or similar orchestration frameworks. * Experience with LLM and RAG evaluation approaches (Azure toolset preferred: Azure Foundry, ML Studio etc.). * Knowledge of retrieval-quality metrics and controlled experiment design. * Experience with Docker, Kubernetes, telemetry and load testing. * Knowledge of knowledge graphs, temporal retrieval or document-linkage techniques. * Experience developing AI solutions within regulated or specialist knowledge domains. * Understanding of Generative AI monitoring and protection frameworks (preventing prompt injection, misuse and monitoring costs, tokens, update etc.) ## Description Successful candidate will develop modular Python services across question planning, AI workflow orchestration, information retrieval, evidence processing, LLM integration, response generation and validation. You will work collaboratively with engineering, data, platform and evaluation specialists to translate AI concepts and experiments into reliable, scalable and maintainable production services. This is a hands-on software engineering role requiring strong production Python experience and practical delivery of Generative AI and RAG systems. Key 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. ## Related Videos - [How E.On productionizes its AI model & Implementation of Secure Generative AI.](https://www.wearedevelopers.com/videos/623-how-e-on-productionizes-its-ai-model-implementation-of-secure-generative-ai) - [Docker Compose: Rediscovered](https://www.wearedevelopers.com/videos/1978-docker-compose-rediscovered) - [pytest: Simple, rapid and fun testing with Python](https://www.wearedevelopers.com/videos/213-pytest-simple-rapid-and-fun-testing-with-python) - [How a Small Team Shrank a Microsoft Monorepo by 94%](https://www.wearedevelopers.com/videos/1236-how-a-small-team-shrank-a-microsoft-monorepo-by-94) - [Docker build without Docker](https://www.wearedevelopers.com/videos/100114-docker-build-without-docker) - [Agents for the Sake of Happiness](https://www.wearedevelopers.com/videos/1387-agents-for-the-sake-of-happiness) ## Related Articles - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development) - [ Dev Digest 213: Petrol Prices, Agentic Workflows, AI Skills and CODE100!](https://www.wearedevelopers.com/magazine/718-dev-digest-213-petrol-prices-agentic-workflows-ai-skills-and-code100) - [Dev Digest 137 - AI'm not sure about this](https://www.wearedevelopers.com/magazine/485-dev-digest-137-ai-m-not-sure-about-this) - [Got AI ideas but no money? Here are 10 free ways to level up your AI skills with Google Cloud](https://www.wearedevelopers.com/magazine/600-got-ai-ideas-but-no-money-here-are-10-free-ways-to-level-up-your-ai-skills-with-google-cloud) - [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline) - [13 AI Tools You Have to Try](https://www.wearedevelopers.com/magazine/219-13-ai-tools-you-have-to-try)