Our client is seeking an experienced AI Engineer to take the technical lead on the development and delivery of innovative, Generative AI solutions within a cross-government digital programme.

This is a hands-on, senior engineering role focused on Large Language Model (LLM) technologies, Python-based API development, and AI product innovation. You’ll play a key role in maintaining and enhancing a high-profile Generative AI service used across the public sector, while also contributing to new experimental AI initiatives.

The successful candidate will work alongside Developers, Data Scientists, and Product Managers to deliver cutting-edge solutions that leverage synthetic audiences, retrieval-augmented generation (RAG), and data-driven insights to support decision-making and communication across government.

This is a fantastic opportunity to work at the forefront of responsible, impactful AI in the public sector.

Key Responsibilities

*

Maintain and enhance an existing FastAPI-based service hosted on AWS Elastic Beanstalk.

*

Develop and deliver new product features aligned with an existing roadmap, including data ingestion, RAG pipelines, and agentic AI extensions.

*

Lead experimental AI workstreams, transforming audience data and insights into AI-powered synthetic personas and audiences.

*

Contribute to AI solution design, including prompt engineering, retrieval systems, and Generative AI model integration.

*

Work closely with Product Managers, Developers, and Data Scientists to ensure timely, high-quality delivery within agile sprints.

*

Take ownership of the full development lifecycle — from build and testing to deployment and performance monitoring.

*

Contribute to documentation, technical governance, and agile project processes.

Minimum Requirements

*

Proven experience with Large Language Model APIs (from 2021 onwards).

*

Hands-on experience developing Generative AI solutions and integrating them into production environments.

*

Strong Python programming experience, ideally with FastAPI, asyncio, and SQLAlchemy.

*

Experience building LLM-powered applications with tool use and information retrieval capabilities.

*

Working knowledge of AWS infrastructure and deployment workflows.

*

Proven ability to work effectively within agile, cross-functional teams.

*

Strong communication skills and ability to take ownership of technical delivery.

*

No front-end development experience required.

Interview Process

1.

Light-touch coding session (candidates may use any resources).

2.

Interview with the project team