Contact
Book a 30-minute technical diagnosis
Share the business context first. I will help assess whether the AI application is worth building, how to approach it, and where the main risks are.
Projects
These projects show what problem each asset solves, which stack it uses, and how it can be reused.
A multi-tenant SaaS backend that wraps ComfyUI workflows with permissions, credits, node allowlists, and DAG-based production flow governance.
A long-running training-data pipeline core using relational corpus storage, DB cursor state, Redis pause flags, and idempotent upsert writeback.
An offline training toolchain that cold-starts multimodal social-media data into a Chinese domain LLM that flags illegal securities activity and explains why.
An engineering pipeline that extracts asset-management contract clauses into standard rules and generates daily subscription/redemption calendars.
A report-pipeline AI project for a large health check provider, covering package recommendation, medical education, recommendations, and contradiction detection.
An engineering pipeline for extracting, verifying, and evaluating structured fields from private fund contracts.
A macro research pipeline that turns reports, news, policy signals, and economic indicators into traceable asset allocation reference reports.
An enterprise RAG assistant for investment research, with multi-turn Q&A, hybrid retrieval, streaming answers, and traceable evidence.
Contact
Share the business context first. I will help assess whether the AI application is worth building, how to approach it, and where the main risks are.