Senior AI Engineer

The Portfolio Group Inc.; Manchester; On-site; GBP 100,000 - 140,000; Full time

Job summary

The Portfolio Group is recruiting on behalf of our client for an Office based Senior AI Engineer in Manchester. You will work hands-on on real AI products, pushing beyond PoCs to reliable, scalable solutions. Focus areas include retrieval, model performance, evaluation, and cost considerations.

You will build RAG pipelines, develop GenAI applications, tune models, and design evaluation frameworks. Collaboration with engineering and platform teams will drive production readiness and measurable

Qualifications

• Strong experience with model evaluation, experimentation and fine-tuning.
• Solid hands-on experience building and deploying RAG and GenAI solutions.
• Good understanding of LLMs, embeddings, vector databases and retrieval techniques.
• Experience with Azure AI Foundry would be advantageous.
• Someone who enjoys solving complex technical problems and can explain the thinking behind their approach.

Responsibilities

• Building and improving RAG pipelines, including retrieval strategies, chunking, reranking and grounding.
• Developing GenAI applications and agentic workflows using tools such as LangChain, LangGraph or similar frameworks.
• Working on model adaptation, fine-tuning, instruction tuning and optimisation.
• Designing evaluation frameworks to measure retrieval quality, hallucinations, answer accuracy and overall model performance.
• Experimenting with different models and approaches to improve reliability, latency and cost.
• Taking AI solutions from development into production, working closely with engineering and platform teams.

Skills

model evaluation, experimentation and

RAG solutions

GenAI solutions

LLMs and embeddings

retrieval techniques

Azure AI Foundry

problem solving

explain thinking

Job description

Office based opportunity

We're looking for a Senior AI Engineer who has moved beyond proof of concepts and knows what it takes to build reliable, scalable AI solutions.

This is a hands-on engineering role where you'll be working on real AI products, tackling challenges around retrieval, model performance, accuracy and evaluation.

What you'll be working on:

• Building and improving RAG pipelines, including retrieval strategies, chunking, reranking and grounding.
• Developing GenAI applications and agentic workflows using tools such as LangChain, LangGraph or similar frameworks.
• Working on model adaptation, fine-tuning, instruction tuning and optimisation.
• Designing evaluation frameworks to measure retrieval quality, hallucinations, answer accuracy and overall model performance.
• Experimenting with different models and approaches to improve reliability, latency and cost.
• Taking AI solutions from development into production, working closely with engineering and platform teams.

What we're looking for:

• Strong experience with model evaluation, experimentation and fine-tuning.
• Solid hands-on experience building and deploying RAG and GenAI solutions.
• Good understanding of LLMs, embeddings, vector databases and retrieval techniques.
• Experience with Azure AI Foundry would be advantageous.
• Someone who enjoys solving complex technical problems and can explain the thinking behind their approach.

We're particularly interested in engineers who have genuinely owned AI solutions, understand why certain approaches work (and why others don't), and can demonstrate measurable improvements in model performance.

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