Open to new roles · Remote / contract

Senior Software Engineer, AI · Zotok.ai

Syed Shahbaz Ali

Explore ideas. Engineer solutions. Build systems.

I've spent 5+ years architecting full-stack applications and distributed systems. At Zotok.ai I lead a team building the LLM orchestration layer and scheduled agent workflows behind a multi-tenant B2B AI assistant.

alishahbaz617@gmail.com Hyderabad, India

  • 5+ years shipping production software
  • 16 business tools behind one AI assistant
  • 80% faster initial page load

01 / Experience

Where I've worked

From payments and ERP integrations to browser automation, microservices, and LLM orchestration.

  1. Jun 2023 — Present Hyderabad, India

    Zotok.ai

    Senior Software Engineer — AI

    • LangGraph
    • LiteLLM
    • BigTool
    • Temporal
    • TypeScript
    • Python
    • React
    • Managed a team of 6 engineers, driving best practices and scalable architecture, and running code reviews.
    • Architected the core LLM orchestration layer for a multi-tenant B2B AI assistant spanning 16 business tools, using LangGraph, BigTool, and LiteLLM.
    • Implemented intent classification, dynamic tool routing, structured response generation, and token-budgeted conversation compaction.
    • Built Temporal-scheduled extraction agents for 20+ client WhatsApp groups (72 runs/day, 1k+ messages per tenant), writing structured Google Sheets output from tenant-specific guidance. Migrated the service from Python to TypeScript.
    • Drove frontend performance work that cut initial page load time by 80% and bundle size by 25%.
  2. Nov 2021 — May 2023 Hyderabad, India

    AVRL

    Software Engineer

    • JavaScript
    • Node.js
    • Microservices
    • pnpm
    • CI/CD
    • Engineered resilient browser automation systems in JavaScript, using dynamic selector strategies that replicate human interaction for reliable data extraction.
    • Optimised multiple APIs, improving performance by more than 50%.
    • Sped up the CI/CD pipeline by adopting pnpm as the package manager, reducing deployment time by 70%.
    • Engineered scalable Node.js microservices, improving performance and modularity.
  3. Jul 2021 — Oct 2021 Hyderabad, India

    Mytra Money

    Software Engineer Intern

    • React
    • REST APIs
    • OAuth 2.0
    • Razorpay
    • Developed an ERP system integrated with banking services, including a dynamic JSON-driven component rendering engine in React.
    • Developed and maintained REST APIs with Google OAuth 2.0 for authentication, identity verification, and third-party account integration.
    • Integrated the Razorpay payment gateway, handling payment order creation and capture through REST APIs.
  4. 2017 — 2021 Education

    Deccan College of Engineering & Technology

    B.Tech, Computer Science

Also worked on

Typebot integration

Brought the open-source Typebot chatbot builder into a monorepo, integrated it with the surrounding platform, and extended it with complex business logic.

  • Typebot
  • TypeScript
  • Monorepo
  • Open source

B2B commerce platform

Built backend services and APIs in NestJS while re-architecting a B2B commerce SaaS platform, alongside modular React/Next.js apps and reusable engineering foundations.

  • NestJS
  • REST APIs
  • TypeScript
  • Next.js

Tally ERP integration

Integrated a desktop application with Tally ERP workflows, including the communication between the Electron client and backend services.

  • Node.js
  • ERP integration
  • Electron
  • React

Micro-frontend platform

Architected a monorepo platform for independently developed apps: shared libraries, application boundaries, Module Federation, and build optimisation.

  • Nx
  • Webpack
  • Module Federation

02 / Side projects

Things I build to learn

Open-source experiments in RAG, local-first sync, prompt optimisation, and backend infrastructure.

RAG · Full-stack

meet-shahbaz-ai

A deployed RAG chatbot that answers questions about my career in the first person. It grounds answers in my resume using hybrid BM25 + KNN search with cross-encoder reranking, and streams responses in real time.

  • FastAPI
  • React
  • LangChain
  • ChromaDB
  • Groq
CRDT · Local-first

syncwell-localfirst

An offline-first collaborative editor built on Yjs CRDTs and IndexedDB. Offline edits merge conflict-free on reconnect, and a Node.js WebSocket server with per-room state handles live cursors, presence, and typing indicators.

  • Yjs
  • Node.js
  • WebSockets
  • IndexedDB
  • Tiptap
  • React
LLM · Evaluation

ai-prompt-refiner

A GEPA-based prompt optimisation framework that tests LLM system prompts against real datasets, scores correctness, hallucination, format, and task completion, then iterates toward better prompts.

  • Python
  • GEPA
  • Prompt engineering
  • AI agents
Queues · Reliability

job-queue-and-task-orchestrator

A background-job service. Jobs are persisted in Postgres with a status lifecycle, queued on Redis via Bull, processed concurrently per job type, retried with exponential backoff, and moved to a dead-letter queue when they keep failing.

  • NestJS
  • Bull
  • Redis
  • PostgreSQL
  • TypeORM

03 / Toolkit

Technical expertise

Languages
TypeScript, JavaScript, Python
AI agents & LLMs
LangGraph, LangChain, LiteLLM, BigTool, Tool calling, RAG (BM25 + KNN), SSE, Token & cost tracking
Backend
Node.js, NestJS, FastAPI, Temporal, REST APIs, Microservices
Frontend
React, Next.js, Electron, Redux Toolkit, shadcn/ui, MUI, TanStack Table
Data & search
MySQL, MongoDB, DynamoDB, ChromaDB, OpenSearch
Cloud & infra
AWS, Google Cloud, Docker, CloudFront, S3, Lambda
Build & tooling
Nx, Webpack, Vite, Rollup, pnpm, GitHub Actions

04 / Contact

Have an interesting problem or an idea worth building?

Open to full-time roles, remote work, and contract engagements.

Ask my AI

A RAG chatbot I built that answers from my résumé. The first reply can take up to a minute while the server wakes up.

Open in a new tab How it works