Skip to content
View Mohd-Mursaleen's full-sized avatar

Highlights

  • Pro

Block or report Mohd-Mursaleen

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Mohd-Mursaleen/README.md

Mohd Mursaleen

AI Systems & Backend Engineer — Building intelligent systems that ship.

AI systems and backend engineer based in Bengaluru, India. I build multi-agent orchestration platforms, real-time voice AI pipelines, and production-grade backends. Currently a 3rd-year Information Science student at Sir MVIT (CGPA 8.5).

Portfolio: geekymd.me · LinkedIn: mursaleen-dev · X: @dev_mursaleen · Email: mohdmursaleen1207@gmail.com


Experience

Core Backend & AI Engineer · Stealth Startup (meetchamp.in) · Oct 2025 – Present

  • Architected an AI agent orchestration platform (meetchamp.in/ai) where founders pitch to simulated AI investor personas — 200 users served on launch day
  • Engineered a "second brain" system using non-context graphs, autonomous learning modules, and dynamic persona creation for deeply personalized agent behavior
  • One of three core engineers — owned majority of backend architecture, AWS infrastructure (ALB, SQS), and production deployments

AI Backend Engineer · Eniac (Acquired by Claritel) (claritel.ai) · Mar 2025 – Jul 2025

  • Optimized voice agent initial response time from 8s → 3s (62% reduction) using streaming TTS, context pruning, and VAD tuning
  • Implemented transcription analysis and voice filtering algorithms, improving conversation accuracy by 40%
  • Built automated Plivo CDR retrieval pipeline to identify latency bottlenecks and failure patterns in production
  • Led end-to-end development of the voice agent from client requirements to production delivery

Full Stack Developer · BLDX (getbldx.com) · Aug 2024 – Feb 2025

  • Architected MVC backend containerized with Docker, orchestrated on AWS EC2, with CI/CD optimizations cutting deployment latency by 30%

Full Stack Developer · Opener (opener-ai.com) · Jun 2024 – Aug 2024

  • Engineered complete user onboarding pipeline with personalization via data analytics
  • Built a Chrome extension for automated job application workflows and one-click resume customization

Projects

Hey Agent — Autonomous A2A Networking Platform

  • Agent-to-Agent network where professionals create their AI digital twin in under 2 minutes to autonomously network and evaluate synergies on their behalf
  • Telegram integration for chatting with your agent, configuring preferences, and receiving debriefs of autonomous conversations
  • Python Next.js Telegram API AI Agents

OpenClaw — AI Agent System on Android · Demo

  • AI agent system running entirely on a Redmi Note 7 Pro (LineageOS) — person detection, voice I/O, UI automation, and agent-to-agent networking
  • Person detection via MobileNet-SSD + OpenCV under 50MB RAM, with Telegram photo alerts
  • Python Android OpenCV TFLite Edge AI

AgentForge — No-Code AI Agent Platform · Part 1 · Part 2

  • Full-stack platform to create custom AI assistants, connect them to structured data, and deploy via embeddable iframe widget with real-time WebSocket communication
  • Dynamic Tool Generation pipeline: automatically converts plain-English tasks and raw cURL commands into OpenAI-compatible function schemas using LLM structured outputs
  • Python FastAPI React WebSockets OpenAI

Voice-Controlled IoT Framework · Demo

  • Hardware-software bridge using ESP32 microcontrollers that retrofits any physical appliance into an AI-controlled IoT device
  • Natural conversation or phone call control with ~530ms end-to-end latency
  • Research paper co-authored: Real-Time Voice-Controlled IoT Systems (WebSocket + OpenAI Realtime API)
  • ESP32 Python OpenAI Realtime API WebSockets

SuperFastAPI — CLI for FastAPI · GitHub · npm

  • CLI tool that scaffolds production-ready FastAPI backends with PostgreSQL and Supabase Auth in under 10 seconds — 90% reduction in boilerplate setup time
  • 500+ npm downloads
  • Python CLI FastAPI npm

ProCaptions — Smart Image Overlay Tool · GitHub · Demo · Live

  • Smart image overlay tool for layering elements, custom fonts, and shadow effects in three clicks for social media-ready graphics
  • Python FastAPI TypeScript React

TestPilot — AI Web Testing Automation · GitHub · Demo

  • AI-powered web testing tool using Playwright and LLMs to generate and execute test cases from natural language
  • Python Playwright LLMs Automation

Enterprise Gym Management Platform · Client Project

  • End-to-end full-stack platform delivered for a client; advanced admin dashboard with subscription management, automated messaging, and WhatsApp API integration
  • Node.js React PostgreSQL WhatsApp API

Research

  • Authoring paper on "Dynamic Tool Generation" — novel pipeline that autonomously converts raw data into executable LLM tools, validated to cut development time by ~90%
  • Co-authored published paper on Real-Time Voice-Controlled IoT Systems — sub-second hardware actuation using OpenAI Realtime API and WebSocket architecture

Tech Stack

Languages TypeScript, Python, JavaScript, SQL, Bash
Backend FastAPI, Node.js, LangChain, LangGraph, LangSmith, Pipecat, n8n
Frontend Next.js, React
AI/ML Agent Orchestration, RAG/GraphRAG, Multi-Agent Systems, STT/TTS, Prompt Engineering
Databases PostgreSQL, Neo4j, Redis, MongoDB
Infrastructure AWS (EC2, ALB, SQS), GCP, Docker, Git

Education

Sir M. Visvesvaraya Institute of Technology, Bengaluru B.E. in Information Science · Expected Aug 2027 · CGPA 8.5/10

Pinned Loading

  1. openclaw-android openclaw-android Public

    Run OpenClaw Natively on Android — No Root, No Ubuntu, No proot

    249 25

  2. LiteRT-Server LiteRT-Server Public

    A complete native Android application in Kotlin that runs Google's Gemma 4 E2B multimodal LLM locally on-device via Google's LiteRT-LM SDK.

    Kotlin 31 8

  3. android-automation-agent android-automation-agent Public

    Termux friendly Android Automation skill for you Openclaw

    Python 15 3

  4. trace trace Public

    TypeScript

  5. SuperFastAPI SuperFastAPI Public

    Set Up FastAPI with few clicks

    Handlebars 1

  6. Contento Contento Public

    Intelligent Content Creation Pipeline (Multi-Agent Orchestration)

    Python