Current Work
Founder of MyDocumentIntelligence.com, an AI-driven document intelligence platform for legal and healthcare workflows. The system processes PDFs and contracts end-to-end — applying LLM-driven classification, clause extraction, and risk evaluation to accelerate review — on a hybrid architecture that supports leading frontier cloud models alongside privacy-preserving local models, purpose-built for attorneys and legal-operations teams.
Knowledge Base
This site is a working reference of notes, diagrams, and code patterns accumulated while designing and operating data and ML systems in production. It is organized by domain and kept close to the primary sources.
| Area | Coverage |
|---|---|
| Flagship Project | End-to-end architecture deep dive on MyDocumentIntelligence.com: ingestion, hybrid retrieval + reranking, frontier/local LLM routing, structured citations, RAGAS evaluation, and AWS deployment. |
| LLM Engineering | Production patterns for 2026: agents and Model Context Protocol (MCP), function calling and structured output, RAG evaluation with RAGAS, hybrid search and reranking, vLLM and quantization, LangGraph and DSPy. |
| AI & Machine Learning | Retrieval-augmented generation, vector stores (FAISS, Chroma, pgvector), neural-network architectures, natural-language processing, recurrent models, Hugging Face tooling, and document-ingestion pipelines. |
| Databases | Relational and NoSQL modeling, SQL patterns, graph databases, data streaming, ETL architectures, the Apache ecosystem, and data governance. |
| Databricks | Platform architecture, Delta Lake, PySpark, Spark internals, Mosaic AI Vector Search, Asset Bundles, Liquid Clustering, Genie / AI-BI, migration strategies, and performance tuning. |
| Snowflake | Cortex AI, query optimization, micro-partitioning and clustering, cross-region replication, security posture, and production deployment patterns. |
| AWS | Bedrock (Agents, Knowledge Bases, Guardrails) and SageMaker JumpStart, Redshift, serverless compute, analytics, storage tiers, observability, and security baselines. |
| Algorithms | Data structures, algorithm design, Python reference implementations, and data-transformation patterns. |
| Infrastructure | Containers and orchestration, DevOps tooling, firewall configuration, and Linux system administration. |
| System Design | Architectural patterns, trade-off analyses, and structured frameworks for problem decomposition. |
