Hybrid AI Evaluation Engineer for Public Services

Incubator for Artificial Intelligence; West of England; Hybride; GBP 46 000 - 62 000; Plein temps

Avantages offerts par ce poste

Hybrid working (London, Manchester, or

25+ days’ leave

Dental insurance

Employer pension contribution

Résumé du poste

Incubator for AI in the UK is hiring two AI Evaluation Engineers to focus on model-level evaluation of accuracy, bias and safety, across London, Manchester and Bristol.

You will design evaluation pipelines, run model and system evaluations, and translate findings into practical recommendations for product teams and public services.

You'll collaborate with domain experts, communicate results to technical and non-technical audiences, and help scale evaluation as products grow.

Qualifications

• Experience in a scientific, analytical or engineering role.
• Strong analytical and critical thinking with data insight.
• Knowledge of experimental design and statistical testing.
• Proficiency in Python and version control (git).
• Experience evaluating AI/ML systems and communicating findings.

Responsabilités

• Design and build evaluation pipelines and experiments for AI products.
• Run model and system evaluations for accuracy, bias and safety.
• Collaborate with product and engineering to embed evaluation from day one.
• Partner with domain experts to create golden datasets and benchmarks.
• Translate evaluation outcomes into practical recommendations for teams.
• Explain results to both technical and non-technical audiences.
• Develop reusable evaluation approaches applicable across products.

Connaissances

Python

Git

Experimental design

Statistical hypothesis testing

Data analysis

Communication of results

Outils

Pandas

scikit-learn

Jupyter

Description du poste

Incubator for AI in the UK is hiring two AI Evaluation Engineers to focus on model-level evaluation of accuracy, bias and safety, across London, Manchester and Bristol.

You will design evaluation pipelines, run model and system evaluations, and translate findings into practical recommendations for product teams and public services.

You'll collaborate with domain experts, communicate results to technical and non-technical audiences, and help scale evaluation as products grow.