--:--:--
Loading...

Junior studying computer science at University at Buffalo with a focus in full stack and AI development

I like to develop full-stack applications, build AI-powered tools, and solve complex problems with code.

Om Sethi

Work Experience

Software Engineer Intern - AI
Xircls | June 2025 - Sept 2025
›

Key Achievements

  • Built scalable backend systems with FastAPI and Docker for AI-powered applications
  • Optimized machine learning workflows using LangChain and Ollama for efficient model deployment
  • Developed secure, reliable multi-agent routing systems for complex AI task execution
  • Implemented prompt-based task execution frameworks for enhanced AI interaction capabilities

Technologies

PythonFastAPIDockerLangChainOllamaAI/ML
Co-Founder
Rally | Sept 2025 - Present
›

Key Achievements

  • A volleyball app that combines stat tracking and social networking allowing players to record game performance, share highlights, and connect with teammates

Technologies

GoSwiftpostgreSQLAWS

Projects

AirCommand
In Progress • Computer Vision
›

A real-time hand gesture control system that enables volume control, play-pause, app switching with 95% gesture recognition accuracy and under 200ms response time.

Features

  • Currently developing a real-time hand gesture control system using Python, MediaPipe, and OpenCV with 95% gesture recognition accuracy and under 200ms response time
  • Building a modular gesture recognition architecture currently supporting 4+ gesture types (thumbs up/down, fist, palm) using object-oriented design patterns achieving 25-30 FPS real time processing
  • Implementing a computer vision pipeline that processes live video streaming with 21-point hand landmark detection, featuring two-phase execution system (200ms activation delay + 600ms cooldown) to prevent false triggers

Technologies

PythonOpenCVMediaPipeComputer VisionReal-time Processing
Eden
Completed • AI Security Monitoring
›

An AI-powered security monitoring system that processes 25+ live camera feeds in real-time, detecting incidents (fighting, theft, vandalism) with 92% accuracy and automatically alerting security personnel.

Features

  • Engineered an AI-powered security monitoring system using YOLO across 25+ live camera feeds, detecting incidents (fighting, theft, vandalism) with accuracy improving from 75% → 92%
  • Built a multi-agent verification system using person tracking and spatial analysis to validate threats
  • Integrated real-time video analysis with automated alerting, enabling instant security dispatch via Twilio in under 2 seconds
  • Implemented three specialized AI agents working in real-time: Detection Agent (scans feeds using YOLOv8), Classification Agent (identifies incident types), and Analysis Agent (generates timestamped reports)
  • Developed interactive 3D campus map with real-time camera status visualization and automated footage archiving with thumbnails and metadata

Technologies

ReactTypeScriptNext.jsYOLOPyTorchOpenCVTwilioReal-time Processing
Sonata - Discord Music Bot
Completed • Music Streaming
›

A Discord music bot that streams high-quality audio, supports playlists and queue management and offers interactive commands for seamless group listening.

Features

  • Built high-quality audio streaming with support for YouTube
  • Implemented playlist management with load functionality and queue persistence
  • Created interactive commands for play, pause, and skip
  • Developed user-friendly interface with real-time status updates
  • Added support for multiple voice channels and server-specific configurations

Technologies

PythonDiscord.pyFFmpegYouTube-DLAsyncIO

Skills

Languages

PythonJavaCJavaScriptSwiftGoTypeScript

Technologies

FastAPIDockerOllamaExpoYOLOOpenAI

Tools & Platforms

Visual Studio CodeIntelliJGitEmacsXpraWindowsMacOSLinux (Ubuntu)

Get In Touch

Whether you'd like to talk about projects, opportunities, or just chat, don't hesitate to reach out. I enjoy meeting new people and exploring new ideas.



omsethi205@gmail.com