Tori-Ann H.

AI Systems & Data Engineer | RAG, ETL, LLM, Analytics & AI Agents

I’m an AI Systems & Data Engineer with an M.S. in Data Science from Johns Hopkins. I build production AI and data infrastructure: RAG pipelines, agent workflows, ETL systems, vector databases, analytics dashboards, and cloud data platforms that turn messy operational data into reliable software. My work sits at the intersection of AI, data engineering, data analytics, and applied data science. I can help design the pipeline, clean and model the data, build the dashboard, explain the business story, and connect the system to AI tools like RAG, semantic search, LLM workflows, Pinecone, OpenAI, Claude, Postgres, Snowflake, AWS, or Azure. In practice, that means I work across the full path from raw data to insight to production application. Recent work: • Architected a Postgres ↔ Pinecone sync layer for a 3.6M-document legal research corpus, keeping vector metadata coherent with the transactional store through a revertible, checkpoint-resumable migration protocol. • Canonicalized ~4,000 messy document-type strings into 47 UI-facing categories against a live 57K-docket production database with zero downtime. • Built a custom NLP summarization model for 10-Q filings at the Federal Reserve Bank, extracting quantitative insights for analyst review. Stack: Python, SQL, PostgreSQL, Snowflake, Azure SQL, AWS, Azure Data Factory, Microsoft Fabric, Power BI, dbt, Airflow, Docker, Git, LangChain, OpenAI API, Anthropic API, Pinecone, pgvector, VoyageAI, RAG pipelines, ETL/ELT pipelines. Background: MS Data Science (Johns Hopkins, 3.8 GPA), formerly Hedge Fund Credit Analyst at JPMorgan Chase.