Full Stack AI Engineer

Full Stack AI Engineer
Location: UK remote
Type: Full-time
About us
Handshaik is on a mission to transform how deals get done. Already trusted by leading industry organisations and fuelled by a £1.7m pre-seed raise, we’re building the AI platform of choice for modern dealmakers.
We’re a fast-growing start-up where ideas move quickly from concept to product. Our technology spans backend, frontend, data, and AI, giving our team real scope to shape the future of the product and the company itself. If you’re excited by solving complex problems end-to-end, working in a collaborative environment, and having a tangible impact, you’ll feel at home here.
The role
As a Full Stack AI Engineer, you will work within the development team to help shape the technical vision. This is a hands-on role that requires deep technical expertise, entrepreneurial drive, and the ability to create a scalable solution, from prototype to production. You’ll have the opportunity to build the product from the early stages, solving real customer problems, and playing a key role in the company’s journey towards achieving its business milestones.
Responsibilities (including but not limited to):

• Backend APIs (Python/FastAPI): Build reliable, secure services that power AI features and data retrieval at scale.
  
• RAG & vector search: Design, implement and iterate retrieval pipelines (chunking, embeddings, hybrid search, ranking, feedback loops). Own pgvector/Vector DB schemas, latency, relevance and cost.
  
• LLM integration: Integrate OpenAI/Bedrock models, prompt/response orchestration, tool use, guardrails, and evaluation.
  
• Data pipelines: Ingest and transform structured/unstructured data; design efficient schemas (Postgres/NoSQL) to support retrieval and analytics.
  
• Frontend (React/Next.js): Ship fast, accessible UIs that expose AI features clearly (search, filters, explanations, citations).
  
• Architecture: Evolve a modular, scalable platform (ECS on AWS), with clear boundaries between ingestion, retrieval, reasoning and delivery.
  
• Quality & reliability: Testing (unit/integration/evals), CI/CD, observability (tracing/metrics for LLM and retrieval paths), and performance tuning.
  
• Collaboration: Work closely with Product and ELT; mentor engineers; contribute to technical strategy and research.
  
• Innovation: Research and recommend new tools, frameworks, and approaches for full-stack and AI development.
  We’re looking for…
  
• A passionate individual that’s hardworking and dedicated, with an entrepreneurial/ownership mindset, strong communication skills and a team player
  
• 5+ years of professional experience in full-stack development.
  
• Hands-on experience with RAG systems, vector databases (pgvector/FAISS/Weaviate/ES k-NN), embeddings, and hybrid search (BM25 + vectors).
  
• Strong grasp of chunking strategies, metadata, indexing, recall/precision trade-offs, reranking, and evaluation (ground-truth sets, offline/online metrics).
  
• Strong proficiency in Python (FastAPI) and React/Next.js.
  
• Solid experience with SQL and NoSQL databases (e.g., Postgres, DynamoDB).
  
• Experience working with AI/ML models and APIs (LLMs, embeddings, vector search).
  
• Strong understanding of data engineering practices (ETL, schema design, performance tuning).
  
• Proficiency in cloud environments (AWS preferred) and containerised deployments (Docker, ECS).
  
• Strong grasp of secure coding practices and handling of sensitive data.
  
• Excellent communication, problem-solving, and leadership skills.
  Nice to have
  
• Rerankers (e.g., cross-encoders), structured retrieval over SQL + vectors, query rewriting/expansion, or lightweight knowledge graphs.
  
• LLM/evals tooling (LangChain/LlamaIndex/OpenAI Evals) and feature telemetry for relevance/latency/cost dashboards.
  
• Experience in B2B data products or fintech.
  Get in touch!
  If this role excites you and you believe you’re a strong fit, we’d love to hear from you. Please submit a short cover note along with your CV