Overview

Full Stack AI Software Engineer - Full Remote UK. Base pay range discussed with recruiter. Applicants must be based in the UK with full right to work.

This role requires a software engineer with experience in implementing RAG pipelines and Vector Search (and hybrid AI searches, preferably).

The client is an AI-focused start-up backed by a £1.7M pre-seed investment. They aim to streamline the deal-making process, with founders who have firsthand experience of the challenges in deal processes. Their stack spans backend, frontend, data and crucially AI. This is an opportunity to shape the technical vision of the business and contribute to the product from an early stage.

What you'll work on:

• Backend APIs (Python/FastAPI): Build and maintain secure, high-performance services that drive AI features and data access at scale.
• RAG & vector search: Design and improve retrieval pipelines (embeddings, chunking, hybrid search, ranking, feedback loops), owning schema design, latency, and relevance across vector databases.
• LLM integration: Connect and orchestrate large language models (OpenAI, Bedrock, etc.), manage prompts, tools, safeguards, and evaluation.
• Data pipelines: Ingest, clean, and transform structured and unstructured data; design efficient schemas (Postgres/NoSQL) for search and analytics.
• Frontend (React/Next.js): Deliver user-friendly, performant UIs that make AI-powered features (search, filters, explanations, citations) clear and accessible.
• Architecture: Shape a modular, scalable platform on AWS (ECS), separating ingestion, retrieval, reasoning, and delivery.
• Quality & reliability: Ensure reliability through testing, CI/CD, observability (metrics/tracing for LLM and retrieval paths), and performance optimisation.
• Collaboration: Partner with product and leadership teams, mentor peers, and help shape technical direction.
• Innovation: Explore and recommend new technologies, frameworks, and methods for both full-stack and AI development.

Requirements

• A motivated, hands-on engineer with an ownership mindset, strong communication skills, and a collaborative approach.
• 5+ years’ experience in full-stack development.
• Strong background in RAG systems, vector databases (pgvector, FAISS, Weaviate, Elasticsearch k-NN), embeddings, and hybrid search methods.
• Practical knowledge of chunking strategies, indexing, precision/recall trade-offs, reranking, and evaluation techniques.
• Proficient in Python (FastAPI) and React/Next.js.
• Solid experience with both SQL and NoSQL databases (Postgres, DynamoDB, etc.).
• Exposure to LLMs, embeddings, and vector search APIs.
• Strong understanding of data engineering, schema design, ETL, and optimisation.
• Proficiency with cloud (AWS preferred) and containerised deployments (Docker, ECS).
• Knowledge of secure coding practices and managing sensitive data.
• Excellent communication, problem-solving, and leadership skills.

Nice to have

• Experience with rerankers (e.g., cross-encoders), hybrid retrieval (SQL + vectors), query expansion, or lightweight knowledge graphs.
• Familiarity with LLM evaluation tooling (LangChain, LlamaIndex, OpenAI Evals) and observability for cost, relevance, and latency.
• Background in B2B data products or fintech.

Seniority level

• Mid-Senior level

Employment type

• Full-time

Job function

• Information Technology
• Industries IT Services and IT Consulting