About the Role
This is a hands-on role for someone motivated by outcomes. You will work at the intersection of engineering, product and AI, turning real user problems into production-grade features that ship, perform and improve over time.
- Build and ship AI-powered features embedded directly into customer-facing products, owning them from prototype through to production
- Design and implement end-to-end AI workflows including RAG pipelines, embedding models, vector search and retrieval strategies optimised for real-world accuracy and scale
- Apply techniques such as LLM integration, prompt engineering, chain-of-thought prompting and agentic patterns including tool use and multi-step reasoning
- Integrate AI components cleanly into existing backend services and product workflows, holding AI features to the same engineering standards as the rest of the codebase
- Evaluate model performance, latency, cost and reliability in live environments, making trade-offs that balance user experience with operational efficiency
- Iterate rapidly based on user feedback and production behaviour, treating AI features as living systems rather than one-time deliverables
About You
- Strong engineering background with a proven track record of shipping AI-powered features into production
- Deep proficiency in Python including API development, service integration and building maintainable systems at scale
- Hands-on experience with LLMs in live environments, including prompt design, model integration and output evaluation
- Solid understanding of embeddings, vector databases such as Pinecone, Weaviate or pgvector, and retrieval-based approaches
- Familiarity with orchestration frameworks such as LangChain or LlamaIndex and agentic system design
- Strong grasp of production trade-offs across latency, cost, reliability and security in AI systems