Founding AI Engineer

We're helping a leading, early-stage stealth startup building AI-based prediction software. Their core mission is to accurately predict human behaviour at scale.

You will be responsible for building production-grade LLM and agentic workflows that drive critical business decision-making for their users. This means turning customer, market, and operational data into reliable reasoning contexts for their models, and designing robust evaluation, tracing, replay, and quality-control systems for nondeterministic AI outputs. You'll work on counterfactual analysis, forecasting, customer behaviour modelling, and decision support, constantly improving reliability through structured outputs, retrieval, constraints, calibration, tests, and model comparisons. Expect to build internal tools that make these AI workflows repeatable across various customer segments and use cases, and to directly help define how the team measures the usefulness, accuracy, and trustworthiness of the AI's pre...