As technical lead and AI architect for a civil engineering firm, I designed and built an end-to-end technical report generation system combining multi-source document ingestion, LangGraph-based AI agents with structured output, and human-in-the-loop verification. Leading an interdisciplinary team of frontend, backend, and product professionals in a client-facing role, I architected both the AI pipeline and full-stack infrastructure to automate report creation from specialized document types while maintaining quality control through integrated review workflows.
For a fintech company with strict data isolation requirements, I designed and implemented an AI-powered financial data analyst enabling natural language queries over sensitive multi-tenant data. The system combines AWS Bedrock Claude Sonnet 4 with a 5-layer defense-in-depth security architecture, leveraging PostgreSQL Row-Level Security to ensure users can only access data for their authorized business entities while maintaining audit trails and preventing data modification.
For a sports media organization running a production translation service across multiple languages and sports domains, I designed and implemented a comprehensive evaluation framework using COMET-22 and XCOMET-XXL metrics. The system enables data-driven optimization through automated quality assessment, A/B testing of algorithm variations, and continuous production monitoring without requiring human reference translations.
For a sports media organization with a rigid translation system limited to 5 languages, I designed and implemented OpenSearch-based hybrid retrieval combining BM25 lexical matching with neural semantic search and MMR diversity optimization. The solution replaced static CSV/JSON example storage with dynamic, relevance-based few-shot selection and sophisticated three-tier glossary matching, enabling scalable multi-directional translation across multiple sports domains.
For a fintech company managing financial data across multiple business entities, I architected and implemented a unified data platform combining event-driven data replication, batch API ingestion, and multi-tenant security via PostgreSQL Row-Level Security. The system consolidates data from heterogeneous sources into a centralized analytical warehouse with DBT-automated RLS policy deployment, enabling secure self-service analytics while ensuring strict data isolation between business entities.
For a fitness technology startup, I developed an AI-powered personal fitness coach that generates fully personalized workout plans through multi-stage conversational interaction. The system uses a LangGraph state machine with three specialized agents powered by GPT-4 to gather user requirements, generate structured workout plans, and present them in a human-friendly format.
For a financial analysis firm processing corporate financial documents, I developed a RAG system that combines vector search with graph-based provenance tracking. The solution enables natural language queries across complex financial documents while maintaining complete traceability of information sources through Neo4j’s native graph capabilities.
For a customer service organization processing thousands of daily support conversations, I developed an automated summarization system using fine-tuned FLAN-T5. The solution generates concise summaries for management review, reducing manual analysis time and enabling rapid identification of critical issues and customer sentiment trends.
In this project, I collaborated with a client developing a revolutionary non-invasive glucose monitoring system. Our initial focus was on calibrating the physical device to accurately convert raw signal measurements into glucose levels. We began by analyzing chronoamperometry data to identify optimal parameters for the device and establish a robust calibration method.
This project aimed at providing means to compute how likely it is that two bitcoin addresses belong to the same entity.