AI Engineer

Oliver Bernard; Greater London; Ibrido; GBP 75.000 - 85.000; Tempo pieno

Descrizione del lavoro

Oliver Bernard is seeking an AI Engineer for a remote role within the UK, at an early-stage EdTech startup focused on AI-powered assessment. You will build and refine AI-assisted marking, feedback and assessment workflows from requirements to production.

You will work with production Python, LLMs, and related AI systems, evaluating non-deterministic outputs and balancing quality, latency and cost. Some in-person meetups in London may occur.

Competenze

• Experience building and deploying LLM/ML-based systems in production.
• Experience designing evaluations or regression tests for non-deterministic systems.
• Ability to investigate failures systematically and trade off quality, latency and cost.

Mansioni

• Deliver AI-assisted assessment workflows from requirements through production and ongoing improvement.
• Translate marking guidance into rubrics, schemas, prompts and LLM programs.
• Build and maintain production Python code for assessment workflows and shared AI components.
• Design evaluation methods using representative datasets, regression tests, and statistical analysis.
• Investigate failed or contested assessments and improve workflows accordingly.
• Build human-review and feedback-driven optimisation workflows.
• Extend multimodal assessment capabilities across documents, images and video.

Conoscenze

LLM systems

Regression testing

Failure analysis

AI/ML engineering

Python production

Formazione

Postgraduate degree in AI/ML

Descrizione del lavoro

AI Engineer - Remote (UK) - Early Stage EdTech - £75-85k + equity

Remote within the UK, with occasional in-person meetups in London

I'm working with an early-stage, VC-backed startup building an AI-powered assessment platform, to find an AI Engineer to join their small, fully remote team.

About the Role

You'll build and improve the systems powering AI-assisted marking, feedback and assessment. This means delivering assessment workflows for customers end-to-end - from requirements through implementation, evaluation, production release and ongoing improvement - while also contributing to a shared assessment engine that turns recurring patterns into reusable, configurable capabilities.

This is a hands-on role: production Python, large language models, and other AI systems. You'll investigate failures, evaluate non-deterministic workflows, and make practical trade-offs between quality, latency and cost.

What You'll Do

• Deliver AI-assisted assessment workflows from requirements through production and ongoing improvement
• Translate marking guidance into rubrics, schemas, prompts and LLM programs
• Build and maintain production Python code for assessment workflows and shared AI components
• Design evaluation methods using representative datasets, regression tests, and statistical analysis
• Investigate failed or contested assessments and improve workflows accordingly
• Build human-review and feedback-driven optimisation workflows
• Extend multimodal assessment capabilities across documents, images and video

Core Requirements

• Experience building and improving LLM- or ML-based systems in production
• Experience designing evaluations or regression tests for non-deterministic systems, with real statistical grounding
• Ability to investigate failures systematically and make sound engineering trade-offs
• At least 3 years of relevant AI/ML engineering experience, or a relevant postgraduate degree plus applied experience

Nice to Have

• Experience with prompt/program optimisation frameworks (DSPy, GEPA, AdalFlow) or continuous evaluation workflows
• Experience with multimodal or document-processing systems
• Experience with LLM tracing/eval tools (Langfuse, MLflow, W&B, LangSmith)
• Experience with assessment technology or EdTech

You must be based in the UK and have the full right to work without sponsorship to be considered.

AI Engineer - Remote (UK) - Early Stage EdTech - £75-85k + equity