Senior AI Engineer (Python, React, Azure) in Warrington

About Synextra

Synextra is a Microsoft-specialist Managed Service Provider headquartered in Warrington, operating as a premium partner to regulated mid-market organisations including law firms, financial services firms, and mortgage lenders. We're deliberately small - around 35 people - because we believe the best outcomes come from technical depth, not headcount. Our AI Services Division is growing fast, building and deploying intelligent solutions for clients across the UK. This is a chance to shape that function from the inside - the architecture, the standards, and the products.

The Role

You'll drive the technical architecture behind Synextra's AI platform - designing scalable systems, leading technical decisions across the Python and TypeScript stack, and designing solutions that run securely and cost-effectively within our Azure estate. This is a hands-on role at the intersection of software engineering and applied AI, where your architectural choices directly shape what we ship to clients.

Day to day, you'll work across the full delivery lifecycle: designing multi-agent orchestration pipelines and RAG patterns on the backend, building performant React frontends that surface AI-driven insights, and collaborating with customers, product owners, and infrastructure specialists to integrate generative AI into real business workflows. You'll own end-to-end technical delivery on our most ambitious projects.

This role suits someone who thrives on complex distributed systems problems, stays close to the rapidly evolving AI landscape, and wants genuine autonomy over how things get built. You'll also play a mentorship role - raising the engineering bar across the team and championing Responsible AI practices as we scale.

Responsibilities

• Design scalable, secure, and fault-tolerant full-stack architectures that seamlessly blend traditional web services with generative AI components, ensuring high availability and resilience across Azure-hosted environments.
• Architect complex backend pipelines in Python, incorporating multi-agent systems, advanced RAG patterns, and prompt engineering strategies within Azure’s enterprise AI ecosystem (Azure OpenAI, Azure AI Search, Document Intelligence).
• Establish and enforce best practices for the TypeScript/React frontend, ensuring a highly performant, accessible, and intuitive user experience for AI-driven tooling, including real-time streaming interfaces and interactive data visualisations.
• Lead the configuration and optimisation of Azure cloud environments, establishing robust CI/CD pipelines with GitHub Actions or Azure DevOps, and ensuring cost-optimised use of Azure AI APIs, GPU compute, and container orchestration resources.
• Set the standard for code quality through comprehensive code reviews, technical design documents, and architectural decision records; mentor junior and mid-level engineers to grow their capabilities.
• Champion Responsible AI practices including model evaluation, bias monitoring, content filtering, and compliance with data protection regulations; define and maintain guardrails for LLM-powered features in production.
• Identifying patterns in recurring issues and engineering permanent solutions.
• Contribute to technical pre-sales and client engagements by providing architectural guidance, solution design, and effort estimation for AI-driven projects.

Requirements

Essential Technical Skills

• 6+ years of professional software engineering experience with a track record of architecting and delivering complex applications from concept to production.
• Expert-level proficiency in Python for backend services, data pipelines, and AI integration, including frameworks such as FastAPI, Pydantic, and async patterns.
• Strong proficiency in TypeScript and React for building production-grade frontends, with solid understanding of state management, performance optimisation, and modern component architectures.
• Deep practical knowledge of integrating and scaling LLM features in production environments, including managing token limits, latency budgets, model grounding, prompt engineering, and structured output parsing.
• Strong understanding of full-stack system design principles including API design, microservices architecture, event-driven patterns, and distributed caching strategies.
• Comfortable working with AI-assisted development tools (e.g. Claude Code, GitHub Copilot) to accelerate delivery of production-grade code.
• Experience with CI/CD tooling (GitHub Actions or Azure DevOps), containerisation (Docker), and Infrastructure as Code concepts (Terraform preferred).
• Working familiarity with Azure cloud services — particularly Azure OpenAI Service, Azure AI Search, and Azure Container Apps — sufficient to design and deploy AI-driven solutions within our existing Azure estate.

Desirable Technical Skills

• Familiarity with LLMOps pipelines, including model versioning, evaluation frameworks, A/B testing, and automated prompt regression testing.
• Familiarity with multi-agent frameworks (e.g. Microsoft Agent Framework, LangGraph) and document intelligence pipelines for structured data extraction.
• Experience with data engineering tooling such as Microsoft Fabric for building analytics and reporting pipelines.
• Experience implementing secure authentication and authorisation patterns (OAuth 2.0, managed identities) in cloud-native applications.
• Familiarity with container orchestration beyond basic Docker (e.g. Kubernetes, AKS).

Personal Qualities

• Strong architectural thinking with the ability to balance pragmatic delivery against long-term technical vision; comfortable making and communicating trade-off decisions.
• Genuine passion for mentoring and knowledge sharing; someone who raises the technical bar for the entire team rather than working in isolation.
• Intellectually curious and self-directed; stays current with the rapidly evolving AI landscape.