Vetted Data Analysts in the DMV

“Built a production AI security compliance assessment system using the OpenAI API that ingests company policy documents, performs RAG over embeddings stored in Supabase/FAISS, and generates executive-level gap and maturity reports mapped to NIST CSF, SOC 2, and PCI DSS. Also developed a multi-agent trading assistant orchestrated with LangChain, combining live market data (Yahoo/Polygon.io), sentiment/technical indicators, LSTM-based forecasting, and LLM-generated recommendations.”

“IFC professional who helped build a supply chain decarbonization fund, running multiple workstreams spanning TA program design, MRV framework build-out, gender inclusion, supplier pipeline development, investor engagement, and engineering partner coordination. Known for critical-path prioritization and executive-ready operating systems (decision trackers, weekly one-page briefs, risk logs) that keep complex, multi-stakeholder initiatives aligned and moving quickly.”

“Data/ML engineer with experience across pharma (Dr. Reddy Laboratories) and financial services (Cincinnati Financial, Capital One), building production NLP and entity-resolution systems that connect messy unstructured text with enterprise SQL data. Delivered semantic search with BERT + vector DB and domain fine-tuning (reported ~35% relevance lift), and builds robust pipelines using Airflow/dbt/Spark with strong validation, monitoring, and stakeholder-aligned rollout practices.”

“Built and deployed a production-style vision-language pipeline that generates structured medical reports from chest X-rays using BioViLT embeddings, an image-text alignment module, and BiGPT fine-tuned with LoRA, delivered via Streamlit and hosted on AWS EC2. Also collaborating experience presenting EDA findings, feature importance, and model performance to Ford managers while working with vehicle parts data at Bimcon.”

“Backend engineer with legal-tech and AI workflow experience: built JurisAI, an end-to-end legal research system using OCR + embeddings + Pinecone vector search to deliver citation-grounded LLM answers with safe failure modes (~90% recall@K). Also led a GW Law metadata migration into Caspio with batch validation and parallel rollout, and has strong FastAPI/GCP production reliability and observability practices.”

“At Provenbase, built and shipped a production LLM-powered semantic search and candidate matching platform (RAG with GPT-4/Gemini, multi-agent orchestration, Elasticsearch vector search) to scale sourcing across 10M+ candidate records and 1000+ data sources. Drove sub-second performance, cut LLM spend 30% with routing/caching, and improved recruiting outcomes (+45% sourcing accuracy; +38% visibility of underrepresented talent) through bias-aware ranking and tight collaboration with recruiting stakeholders.”