Vetted Data Engineers in the Bay Area

“Built and shipped LLM/OCR/NLP-driven document-intelligence workflows in operational environments (EnvoyX and UPS), emphasizing production readiness via explicit state-machine orchestration, confidence gates, and human-in-the-loop review. Demonstrated strong business impact in customs brokerage/document ingestion: 50% fewer customs rejects, 30% higher throughput, SLA adherence improved from 71% to 96%, and platform reliability reaching 99.6% with 78% fewer bad-data incidents.”

“Data-engineering-oriented candidate with hands-on experience building an agentic AI product and operational automation workflows. They described automating inventory-to-ERP discrepancy reconciliation with anomaly detection and daily reporting, and also have practical scraping/automation experience dealing with Cloudflare-protected sites using Selenium and Puppeteer.”

“Startup builder (MagicSeven) who designed and implemented a browser-based, agentic video editor end-to-end, including an AWS event-driven multimodal LLM “indexing” pipeline and an orchestration LLM agent for searching and manipulating footage. Demonstrates deep video file/codec knowledge plus practical production hardening of LLM workflows (format validation, plan/execute, S3-based state for debuggability).”

“Built and deployed a production LLM system that scraped Google Maps menu photos, extracted structured prices via OpenAI, and cross-validated them against website-scraped data to automate data-quality verification at scale (replacing costly manual contractor checks). Demonstrates strong reliability instincts—precision-first prompting, output gating with image-quality metadata, and fuzzy matching/RAG techniques—plus solid orchestration (Dagster/Airflow) and observability (Sentry, Prometheus/Grafana).”

“AI/ML engineer with production experience building a RAG-based internal analytics assistant (Databricks + ADF ingestion, Pinecone vector store, LangChain orchestration) deployed via Docker on AWS SageMaker with CI/CD and MLflow. Strong focus on real-world constraints—latency/cost optimization (LoRA ~60% compute reduction), hallucination control with citation grounding, and enterprise security/governance. Previously at Intuit, delivered an interpretable churn prediction system (PySpark/Databricks, Airflow/Azure ML) that improved retention targeting ~12%.”