Built a RAG chatbot? Great. Taken an AI solution into production, evaluated its weaknesses and made it genuinely better? Now we''re talking.

We''re looking for an experienced Senior AI Engineer to join a growing AI function where the focus is on building intelligent, reliable and scalable solutions that solve real business problems.

This role is for someone who enjoys the difficult engineering challenges behind generative AI: improving retrieval, reducing hallucinations, fine-tuning models and proving that changes genuinely improve performance.

You won''t just be experimenting with the latest frameworks. You''ll be designing, building, evaluating and improving AI systems that are intended to deliver measurable results.

What will you be working on?

• Building and optimising production-grade RAG pipelines, including retrieval, chunking, reranking and grounding.
• Developing advanced GenAI applications and agentic workflows using LangChain, LangGraph and LlamaIndex.
• Working on model training, fine-tuning, instruction tuning and optimisation.
• Designing robust model evaluation frameworks covering accuracy, reliability, consistency and overall response quality.
• Measuring retrieval performance, hallucination rates, groundedness, robustness and safety.
• Exploring evaluation approaches including BERTScore, human-in-the-loop testing and automated evaluation.
• Experimenting with models and architectures to improve performance, latency and cost efficiency.
• Taking ownership of technical solutions from initial design through to production deployment and continuous improvement.
• Collaborating with engineers and stakeholders to solve complex AI challenges.

What will make you stand out?

• Strong hands-on Python engineering experience.
• Proven commercial experience delivering GenAI, LLM or RAG solutions into production.
• Practical experience using LangChain, LangGraph, LlamaIndex or comparable orchestration frameworks.
• Genuine experience in model evaluation, testing and performance improvement.
• Exposure to model fine-tuning, adaptation or training, with an understanding of when these approaches are appropriate.
• Strong understanding of embeddings, vector databases, retrieval architectures and LLM behaviour.
• The ability to explain your technical decisions, evaluate trade-offs and demonstrate the impact of your work.

Experience with Azure AI Foundry would be advantageous.

Why join?

You''ll be joining a business that''s actively investing in AI, with the opportunity to own complex technical challenges and directly influence how AI solutions are built and improved.

You''ll work closely with an ambitious engineering team, contribute to key architectural decisions and have the space to experiment, challenge existing approaches and deliver meaningful improvements.

We''re not looking for someone who can simply connect an LLM to an API. We''re looking for an engineer who understands how to make AI accurate, reliable and production-ready.

Sound like you? Let''s have a conversation.

51752MSR1

INDMANS

The Portfolio Group are acting on behalf of our client in recruiting for this position.