Vetted Front-End Development Professionals

Muhan Zhang

Screened

Junior AI Software Engineer specializing in LLM pipelines, OCR, and RAG

Palo Alto, USA2y exp

“Built and shipped a production LLM pipeline for nursing home Medicare reimbursement (PDF OCR + fact extraction + keyword RAG + QA) that reportedly increased payouts by ~$1K/month per patient. Strong in LLM ops/benchmarking (ground truth, LLM-as-judge, cost/I-O tracking) and pragmatic optimization—swapped retrieval approaches, fine-tuned a small model to cut OCR cost 90%, and migrated workloads to Azure/Temporal to scale nightly processing 10x.”

“AI/LLM-focused engineer with hands-on experience building RAG pipelines, prompt engineering workflows, and multi-agent systems using tools like LangChain. Stands out for combining AI-assisted development with production-grade validation and for leading the architecture/orchestration of agent-based recommendation systems that improved response time, accuracy, and scalability.”

“Engineering leader with hands-on architecture depth who has managed offshore teams up to ~30 engineers across mobile, web, backend, and Roku. Particularly strong in applying AI pragmatically—driving code-generation and review workflows, tailoring model usage by tech stack, and building internal LLM/RAG tools—while also improving operational KPIs through automation, cost optimization, and workflow redesign in content/media environments.”

Robert Davis

Screened

Staff Software Engineer specializing in backend and distributed systems

Remote, US19y exp

“Backend engineer who co-launched SkyKick’s Office 365 SharePoint/Exchange backup product, built the MVP, and then architected and led its design for 9 years. Stands out for high-scale systems expertise, including an algorithmic redesign that cut cloud costs by an order of magnitude, plus earlier experience integrating speech recognition systems in noisy real-world customer environments.”

“Built and deployed PIKA, an internal multi-agent platform for FDA-regulated software development, owning it from concept through production. The candidate combines strong full-stack engineering with rigorous LLM orchestration, human-in-the-loop controls, and production eval systems, delivering measurable impact: 3x more design issues caught, ~90% fewer false positives, and ~40% efficiency gains on documentation-heavy workflows.”

“Built internal banking operations products spanning full-stack dashboards and AI-assisted workflow tools. Shipped a RAG-based assistant using PostgreSQL/Redis retrieval with OpenAI and Claude APIs, and used audit-log measurement plus evals/traces to drive a reported ~30% reduction in manual review time.”