Projects
Selected work across data engineering, AI systems, and enterprise platforms.
Finance RAG — Ask My 10-Ks
A production-grade retrieval-augmented generation system for querying SEC filings. Pose natural-language questions against 10-K and 10-Q disclosures and receive cited, structured answers wherein every claim is traceable to a specific filing page. No hallucinated figures. No guesswork.
- ~2.1s median latency
- ~$0.02 per query
- ≥0.85 RAGAS faithfulness
- 1,260 chunks across 12 SEC filings
- 0–1 blended confidence score per answer
- RAGAS eval gate on every pull request
- RAG
- LLM
- FAISS
- OpenAI
- FastAPI
- Python
- SEC EDGAR
- Cohere
- Langfuse
- LangSmith
- LangChain
- RAGAS
- JWT
- Pydantic
Real-Time Enterprise Data Platform
End-to-end streaming platform on Apache Kafka and Azure Event Hubs, processing 50M+ events per day across distributed microservices with sub-100ms end-to-end latency.
- 50M+ events processed daily
- Sub-100ms p99 latency
- 12 source systems integrated
- Apache Kafka
- Azure Event Hubs
- Apache Spark
- Delta Lake
- dbt
- Azure