Open to work · remote / hybrid / on-siteSenior Full-Stack AI Engineer · MERN

Senior full-stack AI engineer.
MERN, wired into LLM systems.

I'm Yaseen Khatib. Five years of building for the web end to end — React, Node.js, TypeScript, MongoDB — and the last few wiring that stack into production AI: RAG pipelines, agent orchestration, and five products shipped solo, from a Rust desktop app to autonomous pipelines. Everything on this site actually runs. Scroll down and poke it.

Hyderabad, India (IST) · happy remote, hybrid, or in an office · effective across global time zones.

Get in touchDownload CVView live architecture

~/founders-log

A résumé tells you what I did.
This shows you — as it happened.

All dispatches →
0products · solo
0+dispatches
0 dayfastest client ship
  1. 01How I Went From My First Dev Job to Building AI SystemsFive years, honestly told: an ASP.NET healthcare backend in 2021, full-stack MERN through the ChatGPT shift, nights of embeddings homework, and finally shipping five AI products solo. The journey, without the gloss.
  2. 02I Shipped 5 Products in 12 Months — Solo, Unfunded, and Faster Than Most Teams Ship OneFive production systems — a Rust desktop cockpit, a workflow engine, a local-first AI finance agent, and two autonomous pipelines — designed, built, and shipped by one engineer. Here's the operating model.
  3. 03Vision Over Syntax: I Design the Entire Product in My Head Before the First CommitSyntax is solved; vision is not. How architecture-first thinking — data contracts, trust boundaries, and deliberate refusals — is the real engineering skill in the AI era, shown through shipped products.
  4. 04One Architect + Claude + MCP = A Full Engineering Squad: The Operating Model I'd Install at Your CompanyThe exact three-layer operating model — architect, Claude Code, MCP-wired systems — that lets one engineer ship like a squad, and the 30-day plan for installing it inside a real company.
  5. 05Your Company Is Overpaying for AI by 80% — I Built a Live Simulator That Proves ItMost production AI traffic is simple or repetitive, yet it's billed at frontier-model prices. The cache → flash → frontier cascade that fixes the economics, with a live interactive cost simulator.
  6. 06My Networking Runs Itself: The LinkedIn Pipeline That Grew My Reach While I SleptHow I engineered consistency: an autonomous GitHub Actions pipeline that turns real work into scheduled LinkedIn posts, tracks state in Git, costs $0 to run — and what the same pattern automates inside a company.

~/products

View all →
Mobile · AI AgentSableLocal-First AI Financial AgentA privacy-first personal finance agent that keeps 100% of your financial data on-device in SQLite — no cloud backend. An OpenAI function-calling agent tracks debts and pushes proactive briefings, with every database mutation gated behind a Review & Confirm boundary.React Native (Expo)TypeScriptSQLiteZustandDesktop · RuststreamerOSUltra-lightweight streaming cockpitA Rust-powered desktop cockpit for Twitch & YouTube streamers — live system telemetry, multi-platform chat velocity, and automated OBS scene sync, all inside a ~152 MB / 1.8% CPU footprint.RustTauri v2WebSocketsNext.jsAutomation · AgentAutomated LinkedIn PipelineAutonomous content schedulerA Python autonomous agent running on GitHub Actions that schedules and publishes technical content on a cron — drafting every post through the Gemini API. Zero servers, zero manual posting.PythonGitHub ActionsGemini APICronPipeline · ContentZero-Cost AI Blog WriterGit-triggered article factoryA native Next.js pipeline that autonomously writes, formats, and deploys Markdown articles straight to this site — Gemini drafts the MDX, GitHub Actions commits it, and GitHub Pages ships it.Next.jsMDXgoogle-genaiGitHub Actions

RAG Terminal Concierge

Query my experience through a context-grounded RAG pipeline — live execution traces, structured outputs, and no answers outside the indexed corpus.

rag-concierge — zshrunning
portfolio -- interactive-modelive

~/projects

Flagship · Desktop Cockpit

streamerOS

A Rust-powered desktop cockpit for streaming professionals, engineered via modular Claude orchestrations. Handles live system telemetry feeds, multi-platform chat velocity streams, and real-time automated OBS scene synchronization.

AI-ArchitectedRust / Next.jsLive Telemetry
RustWebSocketsClaude AI
system telemetrylive
CPU Load
Chat Velocity
OBS Sync
Local-First · AI Finance Agent

Sable

A personal-finance agent where the AI is structurally incapable of touching the money: every record lives in on-device SQLite (no cloud backend), and the model's function calls render as Review & Confirm cards — it proposes, only a human commits. Serialized writes, offline-first, and a daily on-device briefing.

Propose/Confirm BoundaryZero-CloudOn-Device RAG
React NativeSQLiteFunction CallingTypeScript
SQLiteon-deviceOpenAIfn-callpropose(intent)Review & ConfirmConfirm→ commit
AI Infrastructure · Edge

Portfolio Concierge — RAG + MCP

One Cloudflare Worker, two interfaces: a grounded RAG API that answers questions about my work from a Vectorize index of my 95-article corpus (refusing anything out of scope), and an MCP server — add its URL to Claude and interrogate this portfolio from inside your own AI. Corpus re-embeds automatically after every deploy.

Interview me via MCPGrounding ContractAuto-Reindexed
Cloudflare WorkersVectorizeWorkers AIMCPTypeScript
SERVER
Client Delivery · EdTech

Path Saathi LMS

A free vocational-skilling LMS (“Learning to Livelihood”) for a client sitting on a library of course videos and PDFs. The brief arrived on a Monday — an MVP sketch and a vision of what it should become — and a working platform was live on the dev environment the next day: auth, course delivery for the client's video and PDF content, self-paced learning flow. One day from vision to a URL the client could click.

Brief on Monday → live on dev in 1 day
1-Day DeliveryClient WorkSelf-Paced LMS
Next.jsReactTailwindTypeScript
Workflow Automation

IntegrateX

An interactive workflow-automation environment featuring responsive connectors, processing layers, and directional edge bindings. Developed a custom state Serialization Adapter architecture to optimize graph serialization over the wire.

Achieved 94% reduction in workflow payload size by implementing a custom Serialization Adapter pattern, drastically lowering database I/O.
94% Payload CompressionReact FlowZustand
React FlowZustandTypeScript
triggerlogicoutputwebhook

These are the five flagships — all 13 builds →

~/experience

Jun 2025 — Present

Senior Software Developer · Sparity

Architecting autonomous Agentic workflows and integrating LLMs into production MERN systems — owning intelligent systems from design and orchestration through deployment.

Agentic AILLM IntegrationMERNSystem Architecture

Jan 2023 — May 2025

Full Stack Web Developer · MSA Software

  • Architected and scaled high-throughput Node.js APIs and React frontends, reducing legacy system latency by optimizing MongoDB aggregation pipelines.
  • Transitioned cross-functional teams to modern Next.js and TypeScript standards, eliminating type-related production bugs.
ReactTypeScriptNodeMongoDB

Sep 2021 — Jan 2023

Software Developer (SDE 1) · Manorama Infosolutions Pvt Ltd

  • Engineered robust backend API services and frontend interfaces, establishing core data flow patterns that accelerated feature delivery.
  • Optimized system architecture for concurrent user sessions, improving overall platform stability.
ReactJSASP.NETREST APIs

~/learning-tracks

40+ lessons, free
AI Systems Architect →15 lessons · RAG → agents → FinOpsAnthropic & Claude Development →15 lessons · tools → MCP → multi-agent
03Contact

Have a product to build? Let's ship it.

contact@streamerosai.com+91 8208335028