Vetted AI Engineers in the Bay Area

“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.”

“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.”

“Built an end-to-end mobile + web Q&A marketplace connecting users with professionals, including real-time chat and Stripe-based monetization (products/subscriptions). Hands-on with scaling Firebase/Firestore (subcollections, composite indexing, pagination) and mobile caching/sync challenges. Also created an internal AI-driven report generator that turned chatbot outputs into curated graphs and PDFs for marketing, iterating based on stakeholder feedback.”

“At ReferU.AI, designed and deployed an agentic RAG pipeline that automates multi-jurisdiction legal document drafting, emphasizing hallucination reduction through hybrid retrieval, validation agents, guardrails, and iterative regeneration. Experienced with orchestration frameworks (especially CrewAI) and rigorous testing/evaluation practices including human-in-the-loop review, adversarial testing, and production metrics/logging.”

“Cloud/distributed-systems engineer who has shipped real-time, offline-capable ledger/expense infrastructure and solved tricky cross-layer production bugs (carrier handoff retries causing duplicate writes) using packet captures and device logs. Also built modular Python ETL/catalog pipelines for e-commerce with config-toggled plugins for customer-specific pricing/SKU rules, and iterated product changes directly with on-site fulfillment operators using feature flags.”

“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.”

“Built and shipped a production AI/LLM agent-based, event-driven credit underwriting/decisioning workflow that automated document understanding, retrieval, risk scoring, and compliance checks—cutting turnaround from ~90 days to ~5 minutes while boosting throughput 200x+ and approvals ~50%. Experienced with Airflow/Prefect orchestration, Redis/RabbitMQ queues, rigorous eval/monitoring, and close collaboration with non-technical underwriting teams.”