Skip to content

MasumKabirBiswas

I build AI agents and ML systems that run in production, plus the products around them.

Technical Team Lead at Neuraforz. I design multi-agent systems, voice and speech pipelines and LLM tooling, then ship them with the full-stack apps that let people steer them.

See selected workStart a conversation
Portrait of Masum Kabir Biswas
AI/ML EngineerKolkata, IndiaTechnical Team LeadNeuraforz

Agents I run in productionlive

hermes › split project → openclaw

Selected work

Six systems,all in production.

Demo · Hermes & OpenClaw

Autonomous agent team · Neuraforz

Hermes & OpenClaw

Two self-hosted AI agents on Oracle Cloud that run marketing, SEO, video and lead generation for three brands. You direct them from Telegram.

agents
2
agents
brands
3
brands
scheduled jobs
20+
scheduled jobs
  • Tag Hermes with a project and he splits the work, hands half to OpenClaw, and both commit to GitHub under their own bot accounts.
  • The X agent posts news carousels and videos for Neuraforz, Exzelon and Medeoan through an approval queue with daily caps.
  • The SEO autopilot runs 18 audit playbooks every three days, fixes what it can and pushes a branch for review.
  • The client finder pulls US/EU leads from job boards every day and sends a CSV to Telegram.
  • Python
  • DeepSeek
  • Playwright
  • systemd
  • MCP
  • HyperFrames
  • Tailscale
Live at x.com/neuraforz
Demo · Zap Voice Agent

Real-time AI calling agent

Zap Voice Agent

An AI voice agent that makes B2B discovery calls. It listens, answers from a knowledge base, scores the lead and hands hot prospects to a human.

real-time loop
Voice
real-time loop
grounded answers
RAG
grounded answers
in production
Live
in production
  • Streaming voice loop built on Pipecat: voice-activity detection, Whisper speech-to-text on Groq, Llama 3.1 for reasoning, Kokoro for speech.
  • Answers come from a RAG knowledge base, so the agent stays on the facts of the product it's selling.
  • Every call ends with a lead score; hot leads trigger an n8n workflow that alerts a sales rep.
  • Python
  • Pipecat
  • Whisper
  • Llama 3.1
  • Kokoro TTS
  • RAG
  • n8n
  • MongoDB
Live at neuraconnects.xyz
Demo · Team Tracker

Desktop app + browser extension · Neuraforz

Team Tracker

A privacy-first work-time tracker in the spirit of Hubstaff. A Windows desktop app and a Chrome extension record whether people are working, never what they type, and managers review it in a web dashboard.

Tauri + Rust
Desktop
Tauri + Rust
MV3 extension
Chrome
MV3 extension
auto-updating
v1.1.7
auto-updating
  • Desktop app built with Tauri and Rust: tray icon, consent screen, live tracking indicator, a break button, and in-app auto-updates shipped through GitHub Releases.
  • A Rust agent samples activity and app usage, buffers it in a local SQLite queue so nothing is lost offline, and uploads in batches.
  • A Manifest V3 Chrome extension logs time per website domain only, never full URLs or page content, and hands it to the desktop app over a localhost bridge.
  • NestJS and Postgres backend with timesheets, activity charts and a screenshot gallery, plus a machine-to-machine API that feeds Exzelon’s performance platform.
  • Tauri 2
  • Rust
  • SQLite
  • Chrome MV3
  • NestJS
  • Prisma
  • PostgreSQL
  • Next.js
Live at neuratracker.neuraforz.com
Demo · EventOS 2.0

Event & livestream platform

EventOS 2.0

A SaaS for running events end to end: ticketing, a marketplace, and live streaming with chat, polls and Q&A.

live video
WebRTC
live video
fan-out
SFU
fan-out
GitHub Actions
CI/CD
GitHub Actions
  • WebRTC streaming through a mediasoup SFU, with Socket.IO chat scaled across instances by a Redis adapter.
  • QR tickets issued at checkout and scanned at the door, plus an analytics dashboard with Excel export.
  • Multi-tenant organisations, role-based access and JWT refresh-token rotation.
  • Next.js 16
  • React 19
  • Express 5
  • mediasoup
  • Socket.IO
  • MongoDB
  • Redis
Live at eventosonline.xyz
Demo · NeuraLeads

AI lead-gen SaaS · Exzelon

NeuraLeads

A multi-tenant platform that finds hiring companies, enriches the contacts and runs cold-email campaigns with an AI inbox.

API routes
489
API routes
MCP tools
148
MCP tools
mailboxes
~500
mailboxes
  • Pulls leads from job sources, then enriches people and company data through pluggable adapters.
  • Runs campaigns across about 500 warmed mailboxes, with AI reply suggestions and spam checks.
  • Its MCP connector exposes 148 tools, so assistants like Claude can operate the platform directly.
  • FastAPI
  • SQLAlchemy
  • MySQL
  • Redis
  • Next.js
  • MCP
Live at neuraleads.ai
Demo · AI Video Stack

Generative video studio as MCP tools

AI Video Stack

A self-hosted video studio on a NAS that AI agents call as tools. Ask for a video and you get back a narrated, scored, finished MP4.

MCP tools
~30
MCP tools
1080p render
45 s
1080p render
video pipelines
13
video pipelines
  • About 30 MCP tools covering script-to-speech (Kokoro, voice cloning), Whisper word timing, music, mixing and loudness checks.
  • Renders with Remotion and HyperFrames pipelines, and cuts long videos into shorts automatically.
  • Per-user API keys, isolated job queues and outputs, so a whole team and the Hermes video agent share one box.
  • Python
  • MCP
  • Whisper
  • Kokoro TTS
  • Remotion
  • FFmpeg
  • Docker

Experience

Junior engineer toteam leadin fourteen months.

  1. Neuraforz (opens company website)

    Full-time · 9 mos · 2 roles

    1. Technical Team Lead

      – · 1 mo

      Kolkata, West Bengal · On-site

      I lead the engineering team and own the architecture of the agent platform and client products.

      • AI
      • Software architecture
      • Team leadership

    2. Software Engineer, AI/ML

      – · 8 mos

      Chicago, Illinois · Remote

      I built LLM agents and Next.js/FastAPI apps, and deployed 10+ live services on VPS infrastructure.

      • Machine learning
      • LLM agents
      • FastAPI
  2. Exzelon (opens company website)

    Part-time · 6 mos

    Application Developer

    – · 6 mos

    Hyderabad, Telangana · Remote

    I build and ship the recruiting and lead-generation products on Next.js and Node.

    • Node.js
    • Next.js
  3. Infomaticae (opens company website)

    Full-time · 4 mos

    Junior Software Engineer

    – · 4 mos

    Kolkata, West Bengal · Hybrid

    I shipped features across Python services and React front-ends.

    • Python
    • React.js

About

The plumbing behindAI that behaves.

I started in Information Technology at MAKAUT and spent the last year putting language models to work: agents that write, publish, audit sites, find clients, render video and hand tasks to each other over Telegram.

Most of what I build is the plumbing nobody sees. That means queues, schedulers, approval gates, tenant isolation and deploy scripts, so an AI system can run unattended without doing something embarrassing.

I'm also studying Biochemistry at Maulana Azad College, because I'm curious where AI meets the life sciences.

GitHub/LinkedIn

Toolkit

AI / ML
  • LLM agents
  • Multi-agent systems
  • RAG
  • Speech (Whisper, TTS)
  • Machine learning
  • MCP servers
  • Claude API
  • n8n
Front-end
  • Next.js
  • React
  • TypeScript
  • Tailwind CSS
  • Motion
Back-end
  • Python
  • FastAPI
  • Node.js
  • Express
  • Prisma
  • SQLAlchemy
Data
  • PostgreSQL
  • MongoDB
  • MySQL
  • Redis
Infrastructure
  • Docker
  • Nginx
  • PM2
  • AWS
  • CI/CD
  • Linux

Education

  • Maulana Abul Kalam Azad University of Technology

    B.Tech, Information Technology

    2021 – 2025 · Grade 8.5

  • Maulana Azad College

    B.Sc, Biochemistry

    2026 – 2028 · In progress

Certifications

Contact

Have a system thatshould run itself?

Tell me what you're building. I usually reply within a day.

[email protected]