Tanveen Bal
About Me
Technologies
C++
Python
FastAPI
Flask
Git
Neovim
CSharp
Java
React
Node.js
PostgreSQL
TensorFlow
Experience
SimInsights
Irvine, CA | January 2025 - May 2025
Built a multi-agent simulation builder for generating 3D simulations from natural language prompts. Integrated an LLM-powered chatbot into the company website for user support and migrated a legacy React app to Next.js for better performance. Deployed backend services connecting LLMs, HyperSkill, and AWS infrastructure.
Tomorrows AI
Remote | September 2024 - December 2024
Built a full-stack European news platform with a responsive UI using React and Vite. Created an article recommendation system using SVD and user behavior data, with AWS DynamoDB for backend. Integrated OpenAI and NewsAPI to deliver live summaries and real-time news content.
USI Networks
Fremont, CA | July 2024 - September 2024
Developed a full-stack inventory management platform to track networking hardware. Built search and filtering features using AWS DynamoDB, React, and JavaScript. Enhanced frontend styling with reusable HTML and CSS components for better usability.
Design and Partnership Lab
Irvine, CA | January 2025 - March 2025
Built a React-based survey platform with Prisma and Tailwind, improving UI for 1,000+ educators. Collaborated with a 7-person dev team to enhance user experience. Partnered with the Chan Zuckerberg Initiative for educational impact.
Ford Motor Company
Irvine, CA | September 2024 - March 2025
Researched autonomous drone systems for emergency response scenarios such as kidnappings and Amber Alerts. Trained a custom YOLO model on Raspberry Pi data for real-time detection of pets and vehicles. Built a Flask app with cosine similarity for target matching and developed a React frontend with live video streaming for rapid remote deployment.
Projects
Minesweeper Deep Q Learning
A reinforcement learning agent trained on 300,000 episodes using Deep-Q Networks to master Minesweeper gameplay.
Chess AI
A chess engine with AI algorithms for move prediction and fully customizable UI with themes and visuals for player engagement.
Car Classyfier
A model that can predict a cars make, model, and body style from an image with 88.76% accuracy, analyzing 280,000+ images.
Leksa
A food-focused social media app, featuring restaurant recommendations and tailored for college communities.
Unbeatable Pong
A retro pong game in C++ with Raylib, featuring classic gameplay, CPU opponent AI, and dynamic gameplay.
Calculator
The calculator system, built on a Tiva microcontroller, uses a keypad for inputs. An LCD display is used to display all calculations being made.
Muli-Threaded WebCrawler & WebSearch Engine
A fast web crawler that improves data retrieval by 400% and filters out unnecessary sites. The search engine ranks results quickly with sub-30 ms response times.
Compiler
Java-like syntax compiler with recursive descent parsing, semantic analysis, and optimizations like Dead Code Elimination for efficient x86 assembly generation.