Collaborate with end-users across trading, operations, and support functions to identify automation opportunities and develop LLM-based solutions tailored to their workflows
Own the agentic-evaluation engine. Build the capability that scores agents on the metrics that matter - intent resolution, tool-selection and parameterisation accuracy, task adherence, planning quality, tool-call ordering, response completeness against a reference, and when an agent should defer to a human.
Maintain, enhance, and debug the homegrown MES application across the full stack — React frontend, C# REST API backend, and Microsoft SQL Server database.
Lead the architectural design, development, and end-to-end performance optimization of enterprise-grade AI Agent systems as a core team member, ensuring reliable delivery under high-concurrency scenarios.
Conduct reinforcement learning (RL) training experiments for long-horizon tasks, including hyperparameter tuning, performance analysis, and iterative optimization.
Technical Strategy and Roadmap: Assess existing systems, identify architectural gaps and define a technical roadmap across data, search and AI. Prioritise investments and determine what to improve, simplify, replace or rebuild.