Sailesh D.

Most AI projects die between the demo and the deploy. I work on the part after the demo: retrieval that has to be right, evals that gate the release, guardrails and the audit trail, cost per request. I've been the sole mobile/full-stack engineer on products that went from nothing to real users — React Native, Flutter, Expo, Vite, Express, Hono, MongoDB, PostgreSQL — so you're not waiting on five different people to ship one thing. WHAT I'VE BUILT → OneTake — mobile lead for a year. Every pivot, every weekend bug, handled. → Solas Compliance — policy-to-rules compliance review for finance and iGaming, with a full audit trail back to source clauses → Rayu — an AI nutritionist paired with a wearable, grounded in live health data → Palete, Sambad — AI agents running customer operations over WhatsApp and omnichannel inbox → Sajilo Sewa — Nepal's home-services marketplace, 50+ services → Flexera — connected fitness hardware + app AI WORK → RAG pipelines, eval suites that gate deploys, cost/latency budgets → Agents and internal workflows with typed tools, permissions, audit trails → OpenAI, Gemini, Claude API integration — production use, not demos → Claude Code, Codex — daily use STACK → Mobile: React Native, Expo, Flutter, Dart → Web: React, Vite, TypeScript → Backend: Express, Hono, Node.js → Database: MongoDB, PostgreSQL → Cloud: Firebase, AWS, GCP I reply within 12 hours. Scope is clear? I can usually start the same day. Drop me a message — glad to take a look at what you're building.