AI Engineer

Peaple Talent; Greater London; On-site; GBP 100,000 - 120,000; Full time

Job summary

A dynamic technology startup in London is seeking a Founding AI Engineer with a focus on backend services powered by AI. This role requires expertise in integrating LLM APIs and designing RAG pipelines to enhance AI features. The ideal candidate will work closely with the founding team to build cutting-edge AI solutions that transform how services are accessed. A competitive salary package of £100–120K plus equity is offered in a fast-paced startup environment.

Qualifications

• Experience architecting and building backend services for AI applications.
• Proficiency in integrating LLM APIs and open-source frameworks.
• Familiarity with designing RAG pipelines and using vector databases.

Responsibilities

• Architect and build AI-driven backend services for semantic search.
• Integrate and deploy LLM APIs and AI frameworks into production.
• Design and optimise RAG pipelines for enhanced AI workflows.

Skills

AI-driven backend services

Integration of LLM APIs

RAG pipelines

Knowledge graphs

Multi-step AI workflows

Tools

OpenAI

Anthropic

Cohere

LangChain

Pinecone

Weaviate

FAISS

Job description

Job Description

Founding AI Engineer (Backend) – London – £100–120K + Equity

Are you an AI engineer who loves turning cutting‑edge AI into real products? This London-based startup is transforming how service providers and customers connect, and is looking for a founding AI engineer to help design and build the core of its AI platform.

AI is central to the product, powering semantic search, intelligent matching, assistants, and personalised experiences across web and mobile. You’ll work closely with the founders to design and deliver creative AI features that genuinely change how people discover and book services.

What you’ll be doing

• Architect and build AI-driven backend services powering semantic search, natural language interfaces, recommendations and assistants
• Integrate and deploy LLM APIs (OpenAI, Anthropic, Cohere) and open-source AI frameworks (LangChain, LlamaIndex, LangGraph) into production
• Design and optimise RAG pipelines using embeddings, vector databases (Pinecone, Weaviate, FAISS) and other retrieval systems
• Work with knowledge graphs and structured data to add richer context and smarter reasoning to AI workflows
• Develop agentic / multi-step AI workflows that call tools, APIs and data sources to automate real user journeys

<...