Vetted Data Scientists in the Bay Area

“Solutions Architect with 5+ years leading pre- and post-sales engagements, focused on taking complex tooling from test/prototype to secure production through a structured discovery-to-deployment approach. Experienced in LLM workflow troubleshooting using tools like Langfuse/Gopher and in developer enablement via concise, hands-on workshops (e.g., Jenkins on Kubernetes at scale). Has navigated internal and external blockers to drive adoption and keep enterprise deals moving (including a Jenkins sale to Love's).”

“LLM/agentic systems builder who shipped production workflows at Angel Flight West and Eureka AI, combining LangGraph + RAG (Postgres/pgvector) with strong observability (LangSmith/Langfuse). Delivered large operational gains (address lookup cut from 10 minutes to 60 seconds; accuracy to 92%) and has a track record of quickly stabilizing customer-critical pipelines (Pydantic-enforced JSON for ETL) while partnering with sales/ops to drive adoption.”

“GenAI/LLM engineer with production experience at Allstate building an end-to-end document intelligence workflow for insurance operations—automating document intake, classification, and risk signal extraction. Emphasizes high-reliability design for regulated/high-stakes outputs using schema enforcement, confidence thresholds, validation rules, and human-in-the-loop routing, with metric-driven offline evaluation and production monitoring.”

“LLM/agentic systems builder who has deployed production solutions for a resource management firm, using an MCP-driven architecture with Neo4j + Elasticsearch and a ChatGPT frontend to generate candidate/company “SmartPacks” and answer entity Q&A. Also built a LangGraph/LangSmith-orchestrated multi-agent workflow that automates data-infra change requests end-to-end (impact analysis, SQL + tests, and PR creation), and delivered a ~60% latency reduction through TTL-based context caching while improving accuracy via a business data dictionary.”

“Data scientist at Guardian Airwaves building a RAG-powered quiz generator using Grok AI, with hands-on experience solving hard document-ingestion problems (PDFs with images/tables) via unstructured.io and LlamaIndex. Has deployed production systems on AWS EC2 and brings a pragmatic approach to agent reliability (human-in-the-loop, LLM-based eval, latency/cost metrics) while effectively translating RAG concepts to non-technical stakeholders.”

“Built a production-grade LLM evaluation and regression system that stress-tests models across hundreds of iterations, combining LLM-as-judge, semantic similarity, statistical metrics, and rule-based checks, with results delivered via stakeholder-friendly HTML reports and dashboards. Experienced orchestrating multi-agent RAG workflows using LangChain/LangGraph and event-driven GenAI pipelines in n8n integrating OCR, speech-to-text, and external APIs, with strong emphasis on reliability, observability, and explainable failures.”