Skip to content
View DeepBhupatkar's full-sized avatar
🎯
Building Stuff
🎯
Building Stuff
6 followers · 7 following

Achievements

Achievement: Pull Sharkx3Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pull Sharkx3Achievement: YOLOAchievement: Quickdraw

Block or report DeepBhupatkar

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
DeepBhupatkar/README.md

Heyy there! 👋 I'm Deep Bhupatkar

Associate Software Engineer @ VideoSDK.live | AI Developer & iOS SDK Engineer

About Me

🤖 AI Agent Developer building cascading and real-time inference pipelines with multi-provider plugin support (OpenAI, ElevenLabs, AWS, Google, Deepgram).

🍎 iOS Developer creating on-device speech workflows (STT, TTS, STS) using Swift, Objective-C, ONNXRuntime, and Metal.

⚡ SDK Engineer delivering sub-100ms voice-driven agent responses with secure audio/video streaming features.

Current Work

  • Architecting Python-based cascading and real-time inference pipelines for conversational AI
  • Building on-device speech workflows on iOS using ONNXRuntime and Metal
  • Designing core iOS SDK modules for secure, low-latency audio/video streaming
  • Writing custom plugins and agent orchestration systems for real-time voice interactions
  • Directly supporting client engineering teams with SDK integrations

Tech Stack

AI/ML: Python, PyTorch, Hugging Face, ONNX, ONNXRuntime, Transformers, LangChain, OpenAI API, Whisper.cpp
iOS: Swift, Objective-C, AVFoundation, CoreML, Metal, WebRTC, Combine, CoreAudio
Speech & Agents: STT, TTS, STS, Agent Orchestration, Cascading Pipelines, Real-time Voice SDKs
Cloud: AWS, Google Cloud, REST APIs, WebSocket, FastAPI

Building the future of real-time, intelligent communication experiences - one line of code at a time.

Contact

🌐 Digital Space: https://deepbhupatkar.com
📫 Email: bhupatkardeep@gmail.com
🔗 LinkedIn: linkedin.com/deep-bhupatkar

Feel free to explore my repositories and projects! ✨

Pinned Loading

  1. videosdk-live/agents videosdk-live/agents Public

    Open-source framework for developing real-time multimodal conversational AI agents.

    Python 594 82

  2. swiggy-voice-ai-agent-videosdk-mcp swiggy-voice-ai-agent-videosdk-mcp Public

    Voice-powered AI agent for Swiggy (food, groceries, dineout) using VideoSDK AI Agents framework, Swiggy MCP servers, Google Gemini, and SIP telephony. Supports browser, phone calls, and WhatsApp.

    Python

  3. CoreLLM CoreLLM Public

    Your on-device AI, built the Apple way. A native LLM experience for macOS, iOS, and iPadOS — powered by Swift, SwiftUI, and the MLX framework. Runs locally. Works privately. Feels magical.

    Swift 7

  4. macOS-Chrome-Extension-Bridge macOS-Chrome-Extension-Bridge Public

    Demonstrates how to implement Chrome's Native Messaging API to connect a macOS application with a Chrome Extension.

    Swift 1