Résumé

Technical lead for an early-stage AI platform that automates investment research workflows, including expert interview calls, transcription, and research knowledge management.

• Designed financial data pipelines that combine deterministic processing with LLM-assisted extraction, validation, and enrichment.
• Built backend services for automated expert interview workflows, with a focus on reliability, operational visibility, and safe external integrations.
• Separated sensitive customer research data from shared platform services through a dedicated isolation layer and clean API boundary.
• Created a shared tool layer for AI agents so multiple frontends could reuse the same backend capabilities without duplicating logic.
• Built a knowledge management backend where agents can read and write files, answer research queries, and use vector search with LLM inference.
• Reviewed system designs, wrote risk analyses, and called out critical architecture decisions early so teams could avoid costly rework.

Contracted to improve the backend foundations of a financial data processing and reporting product.

• Reduced report generation time by 60% by optimizing backend execution paths and data aggregation workflows.
• Designed backend APIs and orchestration flows for data analysis and reporting workloads, using containerized services on GCP and Windmill for scalable task execution.
• Introduced a modular execution architecture for multi-language scripts with automatic dependency management, reducing friction in onboarding and deployment.