Freelance AI Chatbot Developers in United StatesFreelance AI Chatbot Developers in United States
AI Campaign Assets + Agents for DTC Growth
    $100k+
    Earned
    21x
    Hired
    5.0
    Rating
    301
    Followers
AI Campaign Assets + Agents for DTC Growth
Web Designer/Developer TreyVititoe.com
    $5k+
    Earned
    3x
    Hired
    5.0
    Rating
    83
    Followers
Web Designer/Developer TreyVititoe.com
Fullstack Engineer (Ecommerce + AI Automation)
    $10k+
    Earned
    3x
    Hired
    5.0
    Rating
    55
    Followers
Fullstack Engineer (Ecommerce + AI Automation)
Fullstack Engineer | 14+ yrs Shipping React,Next.js,Node,AI
    $50k+
    Earned
    7x
    Hired
    4.9
    Rating
    133
    Followers
Fullstack Engineer | 14+ yrs Shipping React,Next.js,Node,AI
Cover image for Led delivery of a cloud-native
Led delivery of a cloud-native K-12 student wellness platform that helps counselors monitor wellbeing, surface at-risk students, and act early—balancing product velocity with FERPA/COPPA-aware design and multi-tenant isolation (API RBAC, PostgreSQL RLS, district-scoped analytics). → Owned technical direction and delivery rhythm across a TypeScript monorepo (pnpm/Turbo): backend API, web app, shared packages, DB migrations, CI/CD gates, and staged deploys to GCP (e.g. Cloud Run), aligning engineering work with roadmap and release risk. → Orchestrated an AI assistant for counselors on Google Vertex AI (Gemini): system prompts, safety settings for K-12, function-calling tool design, multi-round tool loops, and strict separation so UI widgets render from verified tool results—not model hallucinations—with tracing/feedback hooks (e.g. Langfuse) for quality and auditability. → Drove access-control and compliance posture for sensitive student data: role/permission middleware, tenant-scoped queries, and defense-in-depth database policies—documentation and evidence suitable for enterprise security reviews (e.g. SOC 2–style narratives). → Partnered on product and program management: phased feature rollout, PR/branch discipline, and clear ownership of scope vs. risk so pilot schools could onboard without compromising data boundaries. → Shaped integrations and platform boundaries: Firebase auth, Neon PostgreSQL + Drizzle ORM, real-time patterns, BigQuery analytics isolation, and operational practices (testing, lint, type-check) that keep the stack maintainable at scale. → Established a disciplined, AI-accelerated delivery model—not ad-hoc prompting: Cursor rules and Claude skills/agents for repeatable workflows; Husky + lint/type-check/test gates; GitHub Actions CI/CD; Cursor Cloud Agents for automated PR review; and daily monitoring of E2E, coverage, and critical issues—owning AI-orchestrated implementation while enforcing accuracy, consistency, and observability
1
593
AI Video Ads & Avatars · Websites with AI Receptionist
New to Contra
AI Video Ads & Avatars · Websites with AI Receptionist
AI Automation Engineer. I build bots and tools that deliver
New to Contra
AI Automation Engineer. I build bots and tools that deliver
Cover image for Most AI site builders hand
Most AI site builders hand you one page and a prompt box. This one ask four questions and returns a complete, navigable website — Home, About, Services, Pricing, Contact — with working links between them, delivered as a preview URL and a downloadable .zip. WHAT IT SELLS A free homepage (one per day), a full five-page website, or a five-stage sales funnel. Payment runs on Telegram Stars, which is what Telegram requires for digital goods sold inside a bot. HOW IT WORKS A Node.js and Express service on MongoDB, running as a Telegram bot, a Telegram Mini App, and a Discord bot from one codebase. Claude generates the site in a three-stage orchestration — brief, then pages, then CSS — behind a single API client with a daily spend breaker. The payment path is built around one rule: a build that fails after a successful payment must never lose the buyer's money. Generation never throws for content reasons; it returns a result object so the caller can decide. Failures refund automatically, without the buyer having to ask. Pricing is validated server-side from a single catalog, so the client can't propose its own price. Preview and download routes use capability URLs — an unguessable 16-byte slug is the credential — because Telegram's open Link hands the URL to the system browser, which can't carry an auth header, and generated pages link to each other relatively. Operationally: tiered rate limits per user, a one-build-at-a-time concurrency guard, a daily spend cap that pauses builds, and a health endpoint reporting uptime, database state, todays spend, and whether builds are paused. Deployed on Railway from a Docker image, behind a CI pipeline that runs syntax, unit, and end-to-end suites on every push — a red suite blocks the merge, so it never reaches production. Discord runs the free tier as an acquisition channel and routes paying users to Telegram, because Discord has no arbitrary-amount invoice and no bot-callable refund.
0
20
Cover image for A Telegram tap-and-build game where
A Telegram tap-and-build game where players grow a business from nothing. Progress earns in-game stars through play. Real Telegram Stars buy something different: actual business assets, generated and delivered for real. THE DESIGN PROBLEM Two currencies in one interface. The earned currency drives the game loop. The real one crosses from simulation into fulfillment — a player running a fictional business can buy a real one's worth of assets without leaving the chat. The two have to feel connected enough that the purchase is a natural next step, and separated enough that nobody confuses play money for a payment. HOW IT WORKS Node.js, Express, and MongoDB, with a Telegram Mini App front end. The game engine is server-authoritative: the client sends intent — "10 taps" — never outcomes. XP, levels, compounding upgrade costs, passive income, and missions are pure functions, with every balance number in a single catalog file. The money path is the part worth reading. Telegram Stars invoices run through pre-checkout validation to fulfillment. A unique index on the Telegram charge ID means a replayed payment is caught and ignored. Stars debit through a conditional atomic update, so two concurrent purchases can't both succeed. Generation failures after a successful debit refund automatically. Claude is treated as untrusted input. The router validates its JSON, overwrites the user ID with the authenticated Telegram ID, re-derives prices from the catalog rather than trusting the model, and rejects any function outside a four-entry allow-list. Every request carries HMAC-validated Telegram initData, plus a webhook secret. The server returns render-ready screens through a JSON UI contract, so the client holds no prices and no rules. Verified by 33 unit tests and 20 end-to-end HTTP tests against a real database. Rate limiting, structured logs with secrets redacted, health checks, Docker, deployed on Railway.
0
8