Founding Full Stack AI Engineer – AI Product

Remote UK (occasional travel to London or Leeds office)

A VC-backed AI start-up on a mission to transform how deals get done is looking for a Founding Full Stack AI Engineer to join their fast-moving team. You’ll play a pivotal role in shaping the product and technical vision from day one—building a scalable platform that blends cutting-edge AI with a slick user experience.

This is the perfect role for someone who thrives in an early-stage environment, enjoys tackling complex problems end-to-end, and wants their code to have immediate, visible impact.

What You’ll Be Doing

• Backend engineering: Design and build secure, scalable APIs in Python/FastAPI to power AI-driven features and data retrieval.
• Retrieval-Augmented Generation (RAG): Architect and iterate RAG pipelines—chunking strategies, embeddings, hybrid search, ranking, and feedback loops—to maximise relevance and minimise latency.
• Vector search & databases: Own vector schemas and infrastructure (pgvector/FAISS/Weaviate), balancing recall/precision trade-offs and optimising cost/performance.
• LLM integration: Integrate and orchestrate OpenAI/Bedrock models; handle prompt/response flows, tool use, guardrails, and evaluation frameworks.
• Data pipelines & analytics: Ingest and transform structured/unstructured data; design efficient SQL/NoSQL schemas to support high-performance retrieval and analytics.
• Frontend development: Create fast, accessible UIs with React/Next.js, exposing complex AI features (search, filters, explanations, citations) in a clear and user-friendly way.
• Architecture & DevOps: Shape a modular, cloud-native platform (AWS/ECS, Docker), with robust CI/CD, testing, and observability.
• Product strategy: Collaborate directly with the founding team to define the technical roadmap and contribute to research on new AI tools and frameworks.

What Experience You’ll Bring

• 5+ years’ professional full-stack development with solid computer science fundamentals.
• Deep Python (FastAPI) and React/Next.js expertise.
• Proven, hands-on AI engineering experience: building RAG systems, vector/embedding pipelines, and hybrid search solutions.
• Strong understanding of embeddings, metadata design, indexing, reranking, and evaluation (offline/online metrics).
• Proficiency with SQL & NoSQL data modelling and cloud infrastructure (AWS preferred) plus containerised deployments (Docker/ECS).
• Familiarity with LLM tools (e.g., LangChain/LlamaIndex) and evaluation techniques is a strong plus.
• Start-up mindset: independent, proactive, and able to take ownership end-to-end without heavy mentoring.

Why Join

• Founding-team impact with meaningful equity
• Build a groundbreaking AI product from the ground up
• Flexible remote-first UK working, with optional London meetups
• Competitive salary and a culture that values innovation and autonomy

Sound like a good fit? Hit apply and let’s chat!