For a sports media technology company, I designed and built a production AI pipeline that extracts compelling game narratives from live broadcast transcriptions. The system combines a three-stage LLM architecture (parallel extraction across 9 narrative categories, independent judge verification, and top-10 curation), prompt caching optimization for cost efficiency, and structured output enforcement via Pydantic schemas. Through dozens of prompt iteration rounds evaluated by subject matter experts across four LLM vendors (Claude, OpenAI, Gemini, Grok), I converged on Claude Opus 4.6 with a carefully engineered prompt system that produces broadcast-quality narratives grounded strictly in source material.
For one of the largest privately held companies in the US, I engineered the platform infrastructure for a conversational AI book companion — a tool that helps readers learn and apply leadership principles through Socratic dialogue. My work spanned authentication, infrastructure-as-code, observability, reliability, and agent execution, delivering a secure, observable, production-grade platform across three AWS environments.
Building on my initial EV charger site selection model, I redesigned the platform from a single-model kWh predictor into a hybrid scoring system that combines LightGBM demand prediction with a six-dimension composite scoring layer. The model expanded from 19 to 58 features across 10 categories — adding network-specific competitive intelligence, amenity dwell-time compatibility, station reliability metrics, and state-level market indicators. The composite scoring layer then augments ML predictions with traffic quality, amenity fit, demographic strength, competitive dynamics, and equity dimensions, producing transparent 0-100 site suitability scores. A market opportunity bonus rewards supply-constrained markets, a competition penalty discounts saturated areas, and a greedy spacing algorithm constructs deployment portfolios that prevent cannibalization.
For an energy infrastructure company evaluating locations for EV charger installation, I developed a geospatial machine learning pipeline integrating real charging network data, EV registrations, demographics, and traffic to predict weekly electricity consumption. The system analyzes hundreds of potential sites and generates ranked recommendations, enabling data-driven capital allocation for EV charging infrastructure deployment.
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.