Generative AI Engineer - Build & Deploy Production AI Apps

Harrington Starr; England; On-site; GBP 75,000 - 120,000; Full time

Job summary

Harrington Starr is seeking an engineering professional to design and deploy production AI applications using the latest generative models. You will translate ideas from concept to deployment and collaborate with a growing product team to deliver tangible impact.

You will work across LLMs, RAG techniques, and model evaluation, while staying current with AI developments and best practices in cloud environments. This is a hands-on role suited to strong Python engineers.

Qualifications

• Commercial experience building AI applications with LLMs.
• Strong Python engineering skills and production code delivery.
• Experience with RAG, prompt engineering, model evaluation or fine-tuning.
• Knowledge of modern front-end technologies is beneficial.
• Strong understanding of machine learning fundamentals.
• Degree in Computer Science, Mathematics or quantitative discipline (or equivalent).
• Experience with cloud platforms and modern engineering practices is a plus.

Responsibilities

• Build and deploy production-grade AI applications using modern LLMs.
• Design scalable AI solutions that solve complex business challenges.
• Evaluate and improve model performance through experimentation and testing.
• Work closely with users to iterate quickly and deliver high‑quality products.
• Keep up to date with the latest developments across the AI ecosystem.

Skills

LLM AI applications

Python engineering

RAG

Prompt engineering

Model evaluation

Fine-tuning

ML fundamentals

Cloud platforms

Education

CS/Math degree or equivalent

Job description

We're working with an organisation that's making a significant investment in AI, building intelligent products that are transforming the way people work. As part of a growing engineering team, you'll play a key role in designing and delivering production AI applications with real-world impact.

This is a hands-on opportunity for someone who enjoys taking ideas from concept through to deployment while working with the latest advancements in Generative AI.

The Role

• Build and deploy production-grade AI applications using modern LLMs.
• Design scalable AI solutions that solve complex business challenges.
• Evaluate and improve model performance through experimentation and testing.
• Work closely with users to iterate quickly and deliver high-quality products.
• Keep up to date with the latest developments across the AI ecosystem.

What We're Looking For

• Commercial experience building AI applications with LLMs.
• Strong Python engineering skills and experience shipping production code.
• Experience with RAG, prompt engineering, model evaluation or fine-tuning.
• Knowledge of modern front-end technologies is beneficial.
• Strong understanding of machine learning fundamentals.
• Degree in Computer Science, Mathematics or another quantitative discipline (or equivalent industry experience).
• Experience with cloud platforms and modern engineering practices is a plus.