Contract - Software AI Engineer
Requirements
Requires more than four years of software engineering experience, strong Python skills, and experience with production systems, APIs, event-driven services, and LLM applications using techniques such as RAG and evaluation. Candidates should also have AWS, container and Kubernetes, CI/CD, and Spark or similar data-processing experience; experience with financial services and tools such as MCP, Databricks, OpenTelemetry, or AG-UI is preferred or relevant.
Job Description
Job Title: Software AI Engineer (contract)
Location: Hybrid - open to any Deloitte office location (London, Bristol, Birmingham, Manchester, Leeds, Cardiff, Edinburgh, Glasgow). Travel to office 3 days per week
Duration: 2 months
Contract Start Date: ASAP November 2026
Day Rate: Competitive (Inside IR35)
Deloitte
Working with the Deloitte Associate (Contractor) Programme means we can offer you the opportunity to work on a variation of industry and client related projects. Our aim is to retain the best talent and so when your project end date nears our team of Talent Community Advisors will be working with you to look at alternative projects within the firm that suit your experience should you wish to continue with Deloitte.
The Role
We are looking for a hands-on Software AI Engineer to design, build and support production-grade AI agent solutions for one of our Financial Services clients. You will develop Python services, agent orchestration, secure integrations and retrieval pipelines, while contributing to cloud-native delivery, testing, observability and operational stability. The role suits an engineer with strong software fundamentals and practical experience building LLM-based applications in an enterprise environment. Preferably from a Financial Services background.
Responsibilities but not limited to;
- Develop and support AI agent components, orchestration logic and workflow automation.
- Build and maintain MCP servers enabling secure access to enterprise data sources.
- Develop, review and troubleshoot high-quality Python production code.
- Build retrieval pipelines for enterprise content with traceable citations and source attribution.
- Develop Databricks data pipelines and feature engineering workflows for AI solutions.
- Support MLOps processes, including model training, testing and production deployment.
- Build user-facing Copilot experiences and human-in-the-loop review workflows.
- Create evaluation frameworks, testing suites and observability for AI services.
- Leverage AI-assisted development tools to enhance code quality, productivity and security.
- Identify and automate recurring issues to improve platform stability and operational efficiency.
Essential Skills and Experience
- > 4 years software engineering experience, including system design, application development, testing and production support, preferable from Financial Services background.
- Strong Python skills plus experience in at least one of Java, TypeScript or SQL; confident reviewing, debugging and improving production code.
- Practical experience building LLM applications using prompting, tool calling, retrieval-augmented generation (RAG) and evaluation techniques.
- Experience building and consuming APIs and event-driven services, with secure integration of enterprise data sources.
- AWS engineering experience including containers, Kubernetes, CI/CD, application resilience and security.
- Experience with Apache Spark or similar data-processing frameworks and large structured datasets.
- Sound judgement when using AI-assisted development tools, including validation of outputs for correctness, performance, security and data sensitivity.
- Experience with MCP servers, agent orchestration, task queues, Databricks, OpenTelemetry or AG-UI.
Deliverables: Responsibilities but not limited to:
- Deliver a secure, scalable copilot capability that orchestrates agent-based workflows across enterprise systems and supports controlled user interaction.
- Build the data and machine-learning foundations that enable the copilot to provide grounded answers and intelligent recommendations.
- Establish the engineering controls required to make AI agents reliable, measurable and safe for production use
IR35
As a means of managing tax, commercial and reputational risks, Deloitte prohibits the use of Associates through Personal Service Companies (PSCs). All Associates must contract under PAYE arrangements through a Deloitte approved Employment Company (aka umbrella company). All Associates are employed by Employment Companies and assigned to work for Deloitte (as the client). When working for Deloitte, associates are required to comply with certain Deloitte policies. The employment company is responsible for the associates' employment, pay and administrative functions.
Skills
About Deloitte
Deloitte drives progress. Our firms around the world help clients become leaders wherever they choose to compete. Deloitte invests in outstanding people of diverse talents and backgrounds and empowers them to achieve more than they could elsewhere. Our work combines advice with action and integrity. We believe that when our clients and society are stronger, so are we. Deloitte refers to one or more of Deloitte Touche Tohmatsu Limited (“DTTL”), its global network of member firms, and their related entities. DTTL (also referred to as “Deloitte Global”) and each of its member firms are legally separate and independent entities. DTTL does not provide services to clients. Please see www.deloitte.com/about to learn more. The content on this page contains general information only, and none of Deloitte Touche Tohmatsu Limited, its member firms, or their related entities (collectively the “Deloitte Network”) is, by means of this publication, rendering professional advice or services. Before making any decision or taking any action that may affect your finances or your business, you should consult a qualified professional adviser. No entity in the Deloitte Network shall be responsible for any loss whatsoever sustained by any person who relies on content from this page.
View company profile →