Senior AI Engineer - Generative AI, RAG & LLMs

Searchability®; Manchester; On-site; GBP 90,000 - 130,000; Full time

Benefits offered by this job

Cutting-edge Generative AI

Technical ownership and influence

Mentor engineers and shape best pract

Collaborative environment on complexAI

Job summary

Searchability® is seeking a Senior AI Engineer to design, build and deliver production-grade AI capabilities in a Manchester-based team. You will lead development of retrieval-augmented generation (RAG) pipelines and agentic AI workflows, collaborating with platform engineers to ensure scalable, reliable AI systems.

You will mentor engineers, participate in code reviews, and shape best practices in prompt engineering, model fine-tuning and evaluation methodologies across complex AI projects.

Qualifications

• Commercial experience with Generative AI, LLMs and RAG.
• Experience building agentic AI systems and workflows.
• Knowledge of prompt engineering, fine-tuning and model optimisation.
• Experience developing and deploying production-grade AI/ML solutions.
• Understanding of AI evaluation and experimentation techniques.
• Strong software engineering fundamentals and technical leadership experience.

Responsibilities

• Design, develop and optimise production-grade AI solutions.
• Build and maintain RAG pipelines and improve retrieval strategies.
• Implement model fine-tuning techniques and evaluation frameworks.
• Contribute to technical decisions, code reviews and mentoring.

Skills

Generative AI

LLMs

RAG

Agentic AI

Prompt Engineering

Fine-Tuning

Production AI/ML

Python

Azure AI Foundry

Graph-RAG

Tools

Azure AI Foundry

Graph-RAG

Job description

Searchability® is seeking a Senior AI Engineer to design, build and deliver production-grade AI capabilities in a Manchester-based team. You will lead development of retrieval-augmented generation (RAG) pipelines and agentic AI workflows, collaborating with platform engineers to ensure scalable, reliable AI systems.

You will mentor engineers, participate in code reviews, and shape best practices in prompt engineering, model fine-tuning and evaluation methodologies across complex AI projects.