Vetted Embeddings Professionals

“AI Engineering Intern at The Etherloop building the backend for a healthcare lifestyle recommendation app, including a multi-agent RAG-based system that uses curated SME data plus web search to generate personalized supplement recommendations from user lifestyle details and blood biomarkers. Evaluates against 500+ SME ground-truth profiles with ranking metrics and focuses on HIPAA-aligned deployment, privacy/security, and guardrails to reduce hallucinations and unsafe outputs.”

“Full-stack engineer who built and scaled an AI-powered web product (React/Next.js + TypeScript/NestJS) with MongoDB, Redis, and RabbitMQ. Strong in rapid iteration while maintaining production quality—uses versioned APIs, feature flags, CI/CD, and observability (correlation IDs/structured logs) to ship frequently and debug distributed workflows. Also created an internal operations dashboard for real-time visibility and control of background jobs/AI workflows that was adopted quickly by ops and product teams.”

“AI Software Engineer (student employee) at University of Washington IT who helped deploy "Purple," a governed, explainable LLM platform on Azure used by 100,000+ students/faculty/staff. Independently led scalable reliability efforts by building automated agent quality/load/red-team testing and CI/CD health validation (Playwright/Node.js, Azure DevOps), and previously built an explainable AI scheduling assistant for clinical operations at Proliance Surgeons.”

“Built and productionized an LLM-powered internal knowledge search system in a regulated environment, using embeddings/vector DB retrieval with strict grounding and confidence gating to reduce hallucinations. Reported ~45% accuracy improvement over keyword search and implemented end-to-end orchestration, monitoring, CI/CD, and incremental re-indexing to manage latency and data freshness while driving adoption with business stakeholders.”

“Built a production RAG chatbot for Worcester Polytechnic Institute that indexes 500+ webpages using FAISS + Llama 3, with strong grounding/hallucination controls (confidence thresholds and citations). Also has internship experience orchestrating multi-step ETL pipelines with AWS Step Functions and delivered a 30x faster fraud/claims triage workflow at Munich Re using association rules and stakeholder-friendly dashboards.”

“AI/LLM engineer with healthcare domain experience who built a production clinical support “chart bot” for Molina, including PHI-safe ingestion of 200k+ PDF policies, vector retrieval, and a fine-tuned LLaMA served via vLLM on ECS Fargate. Demonstrated measurable performance wins (HNSW + namespace partitioning; 30% inference latency reduction) and a rigorous evaluation/monitoring approach, while partnering closely with nurses and operations teams to shape workflows and guardrails.”