Vetted AI & Machine Learning Professionals in the Bay Area

“Built and productionized an agentic LLM automation system for an insurance client to determine medication eligibility, using prompt-chaining plus a RAG pipeline over policy rules and deploying on AWS (Lambda/Step Functions, Bedrock) with a serverless architecture. Addressed major data/schema mismatch issues via a semantic matching pipeline and validated performance through human agreement scoring, A/B testing, KPI monitoring, and confidence-based human-in-the-loop review.”

“Built and deployed Clyra.AI, an AI-driven daily scheduling product that uses a LangGraph-based multi-agent LLM pipeline (task extraction, verification, reflection) grounded with strict RAG over emails/documents/calendars and real-world signals like health metrics. Designed a custom agent orchestrator with bounded loops/termination conditions and a self-auditing verification/reflection layer to reduce hallucinations while controlling latency and cost via caching and model distillation.”

“ML/NLP engineer with hands-on experience building production systems for unstructured insurance claims and customer data linking. Delivered measurable impact at scale (millions of documents), combining transformer-based NLP, vector search (FAISS/Pinecone), and human-in-the-loop validation, and has strong production workflow/observability practices (Airflow, AWS Batch, Grafana/Prometheus).”

“Governance engineer intern at GSK who built policy-as-code automation using Open Policy Agent/Rego integrated into GitHub CI/CD and Terraform workflows. Also built and shipped a voice-enabled expense tracking app using speech-to-text + LLM structured extraction with strong validation, retries, and semantic guardrails, and designed the supporting PostgreSQL data model with performance-focused indexing.”

“Built and deployed LLM-powered agentic chatbot and text-to-SQL systems using LangGraph/LangChain (and Bedrock), structuring workflows as DAGs with planning/replanning and validation to improve tool-calling reliability and reduce hallucinations. Operates production feedback loops with online/offline metrics, drift detection, and LangSmith-based evaluation pipelines, and regularly partners with business stakeholders and clinicians using slide decks and visual charts.”

“Built a production AI fraud/risk scoring platform at BlueArc that ingests web business/product/site data, generates text+image embeddings, and connects entities in a graph to detect reuse patterns and links to known bad actors. Optimized for scale with incremental graph re-scoring and delivered investigator-friendly explainability by surfacing the exact signals/relationships behind each score; orchestrated workflows with Airflow and GCP event-driven components (Pub/Sub, Dataflow, Cloud Run) and has recent LLM workflow orchestration experience (retrieval, prompting, scoring).”

“Built and shipped Serrano AI, a multi-tenant SaaS conversational AI platform that automates Odoo ERP workflows and lets ops/finance/supply-chain teams query ERP data in natural language. Implemented a multi-agent architecture (LangChain/LangGraph/CrewAI) with hybrid RAG over ERP schemas, deployed on Heroku/Vercel with production observability, cutting reporting time by ~80% while addressing hallucinations, latency, and schema complexity.”