Forward-Deployed AI Engineer

SR2 REC LTD; Greater London; On-site; GBP 90,000 - 130,000; Full time

Job summary

SR2 REC LTD is seeking a hands-on Forward-Deployed AI Engineer to own the end-to-end delivery of a rapid AI proof of concept within a complex regulated enterprise. You will take an initial use case and dataset through to a working prototype, demonstrating how regulatory and compliance information can be queried using modern AI, retrieval and agentic technologies.

Responsibilities include building front-end and back-end components, designing RAG and retrieval capabilities, and integrating

Qualifications

• Strong hands-on AI/LLM engineering experience.
• RAG and retrieval architectures.
• Agentic AI/workflows.
• Strong software engineering capability across front and back end.
• Azure and Azure OpenAI/OpenAI.

Responsibilities

• Own the technical POC from scope through to demonstration.
• Build front-end and back-end components.
• Design and implement RAG and retrieval capabilities.
• Work with vector databases and/or knowledge graphs.
• Develop agentic workflows and supporting harnesses.
• Build evaluation frameworks and assess LLM/retrieval quality.
• Integrate enterprise datasets.
• Rapidly test, iterate and demonstrate solutions.
• Work closely with architects, data specialists and client technical teams.

Skills

Hands-on AI/LLM engineering

RAG architectures

Agentic AI/workflows

Front-end & back-end development

Azure / Azure OpenAI

Tools

Neo4j

Microsoft Graph

Vector databases

Job description

Forward-Deployed AI Engineer

We are looking for a hands-on Forward-Deployed AI Engineer to own the end-to-end delivery of a rapid AI proof of concept within a complex regulated enterprise.

You will take an initial use case and dataset through to a working prototype, demonstrating how regulatory and compliance information can be queried using modern AI, retrieval and agentic technologies.

Key responsibilities

• Own the technical POC from scope through to demonstration
• Build front-end and back-end components
• Design and implement RAG and retrieval capabilities
• Work with vector databases and/or knowledge graphs
• Develop agentic workflows and supporting harnesses
• Build evaluation frameworks and assess LLM/retrieval quality
• Integrate enterprise datasets
• Rapidly test, iterate and demonstrate solutions
• Work closely with architects, data specialists and client technical teams

Experience required

• Strong hands-on AI/LLM engineering experience
• RAG and retrieval architectures
• Agentic AI/workflows
• Strong software engineering capability across front and back end
• Azure and Azure OpenAI/OpenAI
• Experience taking AI prototypes from concept to working solution
• Comfortable independently owning a technical workstream in an ambiguous discovery environment

Exposure to GraphRAG, Neo4j, Microsoft Graph and LLM evaluation frameworks would be beneficial.