Python AI Engineer

Square One Resources; City Of London; Hybrid; GBP 111,000 - 129,000; Full time

Job summary

Square One Resources in London - Hybrid is seeking a Python AI Engineer to design, build and maintain production-grade Python services for Generative AI and RAG solutions.

You will implement LLM workflows, vector and lexical retrieval, and robust testing and monitoring. The contract spans six months with a daily rate of £600–£700 inside IR35.

Qualifications

• Proven experience building production-grade Python services for AI
• Strong async Python with type hints and modular design
• Hands-on with AI orchestration frameworks (Pydantic AI, LangGraph, Semantic Kernel)

Responsibilities

• Design, develop and maintain production-grade Python services for Generative AI and RAG solutions.
• Build and integrate LLM workflows using structured outputs, tool calling, schema validation and controlled fallbacks.
• Implement vector, lexical and hybrid retrieval, metadata filtering, reranking and evidence selection.

Skills

Python development

Asynchronous programming

Testing with Pytest

Distributed services

Code reviews

Tools

Pydantic AI

LangGraph

Semantic Kernel

Azure OpenAI

Azure AI Search

Docker

Kubernetes

Git

CI/CD

Job description

Python AI Engineer

Location: London - Hybrid

Rate: £600 - £700 Per day - Inside IR35

Start: Mid October

Contract - 6 Months

Job Responsibilities/Objectives:

• Design, develop and maintain production-grade Python services for Generative AI and RAG solutions.
• Build and integrate LLM workflows using structured outputs, tool calling, schema validation and controlled fallbacks.
• Implement vector, lexical and hybrid retrieval, metadata filtering, reranking and evidence selection.
• Build asynchronous services with appropriate timeout, retry, cancellation and exception handling.
• Develop automated unit, integration, regression and failure-path tests.
• Implement structured logging, tracing and operational monitoring.
• Monitor and optimise response quality, latency, token usage, cost and performance.
• Contribute to technical design, code reviews, engineering standards and production support.

Required Skills/Experience:

• Strong commercial experience developing production-grade Python applications and services.
• Advanced Python skills, including asynchronous programming, type annotations, modular design and performance optimisation.
• Hands-on experience with Pydantic, LangGraph, MS Agent Framework/Semantic Kernel or similar AI orchestration frameworks.
• Demonstrable experience delivering Generative AI and RAG solutions beyond proof of concept.
• Strong understanding of embeddings, vector search, lexical search, hybrid retrieval, chunking, reranking and evidence selection.
• Experience integrating LLMs using structured outputs, tool calling, prompt/model versioning, token management and response validation.
• Experience building multi-step, agentic or workflow-based AI applications.
• Strong automated testing experience using Pytest or equivalent.
• Experience with APIs, distributed services, Git, CI/CD, containers and production observability.

Technical Skillset:

• Azure OpenAI, Azure AI Search or equivalent AI and enterprise search platforms.
• Pydantic AI, LangGraph, Semantic Kernel or similar orchestration frameworks.
• LLM and RAG evaluation approaches, with Azure Foundry or ML Studio preferred.
• Docker, Kubernetes, telemetry and load testing.

Disclaimer

Notwithstanding any guidelines given to level of experience sought, we will consider candidates from outside this range if they can demonstrate the necessary competencies.

Equal Opportunities

Square One embraces diversity and will treat everyone equally.