AI Engineer

PURPOSE

The AI Engineer turns Source’s specialist research, proprietary market data and industry expertise into reliable, useful AI-powered products and workflows. Source provides market data and insight to the consulting industry, from research reports and survey data to growth figures, forecasts, client perceptions and market modelling. This role will help users query that data, extract insights and draw conclusions with confidence, taking what Source already does well to the next level.

Supported by the Director of Technology and working closely with the Product Owner, software engineers, data analysts, and research teams, you design, build, and operate applications that help colleagues and clients find evidence, analyse data, and generate insights more effectively.

The role is hands-on and focused on delivering business value. It spans document retrieval, structured data, conversational interfaces and workflow automation, and requires choosing the right approach for each problem.

KEY RESPONSIBILITIES

AI applications and workflows

- Design, build and deliver AI-powered applications and workflows that solve real business problems, choosing suitable models and technologies.

- Integrate AI capabilities into Source’s products and internal processes.

- Choose the right approach for each use case and prototype ideas to validate them before production.

Research knowledge and retrieval

- Build and improve search and retrieval over Source’s research content, so users get relevant, traceable answers.

- Ensure users can only access the content they are permitted to see.

Structured data and quantitative analysis

- Build reliable integrations between AI applications and Source’s structured data, such as growths, forecasts, client perceptions and market models.

- Develop tools that help users query data, extract insights and draw conclusions with confidence.

- Make answers transparent and trustworthy, showing users where figures and conclusions come from so they can rely on them.

Evaluation, security and operations

- Evaluate and test AI solutions to ensure quality, accuracy and reliability, using human review where appropriate.

- Monitor application behaviour, usage and cost.

- Work with the Platform team, who own cloud infrastructure and CI/CD, to release and run AI solutions.

- Build appropriate safeguards to keep AI solutions secure and protect data, following Source’s security, privacy and AI approval processes.

- Apply responsible-AI practices, including human oversight, user feedback and transparency about limitations.

Collaboration and knowledge sharing

- Work with Product, Engineering, Data and Research colleagues to identify use cases, shape requirements and prioritise work by business value and feasibility.

- Work with the software engineering team, who build the user-facing front end, to bring AI capabilities to users.

- Communicate system capabilities and limitations clearly to non-technical stakeholders and support user adoption and training.

- Share learning, contribute to code reviews and help build the team’s AI engineering knowledge.

WHAT SUCCESS LOOKS LIKE

In the first six months, you will work with the team to agree a realistic delivery plan and make measurable progress against outcomes such as:

- Delivering production-ready AI capabilities over an agreed subset of Source’s research reports and structured data (such as growths, forecasts, client perceptions and market models), with citations, accurate and traceable answers and permission-controlled access.

- Beginning to establish reusable practices for evaluation, monitoring and security, and identifying further opportunities with Product, Engineering, Data and Research.

- Demonstrating evidence of improved research efficiency, client self-service, user confidence or product capability, compared with a baseline established at the start.

The initial scope will be agreed with the Director of Technology and Product Owner, considering data readiness, the product roadmap, and engineering capacity.

THE TYPE OF PERSON WE NEED IN THIS ROLE

Essential

- Around three or more years' experience in software engineering, AI or ML engineering or a closely related role, with evidence of delivering and maintaining software used by real users.

- Hands-on experience building applications that use LLMs, either in production or as substantial prototypes, including prompt design, model/API integration and structured outputs or tool-calling.

- Curiosity and desire to keep up with new AI capabilities, but also ability to choose technology based on the problem, evidence and operational trade-offs.

- Strong Python skills and experience designing and integrating REST APIs.

- Experience working with structured or quantitative data, with a strong focus on accuracy, including validating numerical outputs from AI systems.

- Experience measuring the quality of LLM or retrieval outputs, such as building test question sets and checking factual grounding.

- Understanding of LLM-specific security risks, such as prompt injection, data leakage and unsafe tool use, and of practical mitigations, including access control over retrieved content.

- Experience testing, debugging and operating production software, including attention to reliability, security, performance and cost.

- Clear communication skills and the ability to work constructively with technical and non-technical colleagues to understand business problems and deliver iteratively, including explaining system limitations

Desirable

- Experience with managed AI and search services (such as Amazon Bedrock or OpenSearch), and with processing complex PDFs or research documents, including tables.

- Experience with tracing, monitoring and observability tooling for LLM applications.

- Experience building automated evaluation and regression testing for LLM and retrieval systems.

- Experience with agent frameworks or multi-step orchestration, and judgement about when not to use them.

- Experience working within governance, privacy or regulatory approval processes such as GDPR.

- Practical SQL skills and experience working with structured data; able to reason about query correctness and validate analytical results.

DIVERSITY & INCLUSION

At Source, we are committed to encouraging equality, diversity, and inclusion among our workforce, and eliminating unlawful discrimination.

We are determined to ensure that no applicant or employee receives less favourable treatment on the grounds of gender reassignment, age, disability, religion or belief, sex, sexual orientation, marital status, or race, or is disadvantaged by conditions or requirements which cannot be shown to be justifiable.

The aim is for our workforce to be truly representative of all sections of society and our customers, and for each employee to feel respected and able to give their best.