Open to ML Engineer & Data Scientist roles

Hi, I'm
Tarosh
Gurramkonda

Building intelligent systems with deep learning, computer vision, and data science. Certified by Stanford, Harvard, and DeepLearning.AI.

2074 Chess Elo (Blitz) Peak
9 ML / DS Certifications
21+ Projects Built
5K+ Game Downloads

From the chessboard
to neural networks

I've always been drawn to strategic thinking. As a kid, I spent years competing in chess tournaments nationally and internationally, developing a mindset that thrives on pattern recognition and calculated decisions.

That mindset led me to game development — I built and released games with a friend during my indie game dev period, gathering thousands of downloads. But I wanted to go deeper: into the algorithms that make machines think.

Today, I specialize in machine learning, deep learning, and computer vision. I've completed certifications from Stanford, Harvard, and DeepLearning.AI — and I'm building projects that apply these skills to real-world problems.

♟️
Chess Strategy
2074 Peak Blitz Elo — pattern recognition, game theory, minimax algorithms
🎮
Team Builder
Built and shipped indie games with thousands of downloads
🤖
ML Specialist
Computer vision, CNNs, NLP, regression models
📊
Data-Driven
Full ML pipeline: data → features → training → deployment

What I work with

A solid foundation across the ML/DS stack — from data wrangling to model deployment.

🐍

Python

Primary language
🧠

Machine Learning

sklearn, XGBoost, ML theory
🖼️

Deep Learning

TensorFlow, PyTorch, Keras
👁️

Computer Vision

OpenCV, CNNs, object detection
📈

Data Science

Pandas, NumPy, visualization
🧮

Linear Algebra

Matrix ops, gradients, optimizations
🌐

JavaScript / Node.js

Full-stack web development
🗄️

SQL / MySQL

Database design & queries
🔧

Git / GitHub

Version control, collaboration
🎮

Unity / C#

Game development, 3D modeling
♟️

Algorithms

A*, minimax, pathfinding
☁️

ML Deployment

Flask, API integration

Building things that work

A selection of ML, data science, and full-stack projects. Filter by category to explore.

Live on Twitch
🛠 In Progress
Real-Time Chess Detection

Building a real-time computer vision system that watches a chessboard through a camera, detects piece positions, and generates chess notation (PGN) live. No expensive hardware — just a camera and deep learning.

Uses Faster R-CNN for piece detection and synthetic data from Blender to train without hand-labeling thousands of images. Iterated through board warping, Hough transforms, and SuperPoint before landing on the current architecture. Streaming the build live on Twitch.

Computer Vision Faster R-CNN PyTorch Blender Synthetic Data Python
🧠
Faster R-CNN + Synthetic Data Pipeline
Automated 10K+ training images from Blender. No hand-labeling. SQLite checkpointing for resilient data collection.
Real-Time Inference → PGN
Detects board + pieces from camera feed, converts positions to chess notation in real time. Goal: record live games end-to-end.
🔁
Iterative Architecture Evolution
Evolved from corner warping → Hough transforms → SuperPoint → Faster R-CNN with dedicated board + piece detectors.
🧠

Real-Time Chess Detection 🔴

Computer vision system that watches a chessboard through a camera and generates PGN notation live. Built with Faster R-CNN and a Blender synthetic data pipeline — no hand-labeling required. Currently in progress.

Computer Vision Faster R-CNN PyTorch Blender
🔍

Celebrity Look-Alike

Face recognition pipeline that compares a user's face against a celebrity database using CNN-based embeddings and cosine similarity to find your celebrity twin.

Python Face Recognition CNN Deep Learning
♟️

Chess AI Engine

Standalone chess engine implementing minimax with alpha-beta pruning and iterative deepening. Evaluates board positions using material + positional heuristics.

Python Minimax Game Theory Alpha-Beta
🏷️

Object Detection Auto-Labeler

Automated labeling tool for computer vision datasets — uses a pretrained model to suggest bounding boxes, cutting manual annotation time significantly.

OpenCV Computer Vision Python Automation
📈

Linear & Multivariable Regression

From-scratch implementations of linear regression and multivariable regression using gradient descent and the normal equation. Both in JavaScript.

JavaScript Gradient Descent Normal Equation
💬

Real-Time Group Chat

Full-stack group messaging app built with PHP, MySQL, and JavaScript. Supports real-time message delivery, user accounts, and persistent chat history.

PHP MySQL JavaScript
📹

Group Video Chat

Browser-based multi-person video chat using PeerJS and WebRTC. No plugins required — pure JavaScript peer-to-peer connections in the browser.

Node.js PeerJS WebRTC
🎮

DDS Multiplayer Games

Built 4 multiplayer games — Rock Paper Scissors, Tic-Tac-Toe, Connect 4, and Chess — all in C++. Used Fast DDS (Data Distribution Service) with a publish-subscribe architecture to enable real-time multiplayer functionality across all games.

C++ Fast DDS Pub/Sub Architecture Multiplayer
🚗

Drive to Infinity

Endless driving game built in Unity during my indie game development period. Navigate an infinite road, dodge traffic, and chase your high score.

Unity C# Game Dev
🏎️

Fun Car Simulator

Freeroam car simulator with custom physics and 3D modeling, built in Unity. One of my first shipped games that accumulated thousands of downloads.

Unity C# 3D Modeling
✈️

Planely Impossible

Infinite runner with a high-score chase. Pilot a plane through increasingly impossible obstacles. Simple, addictive, and competitive.

Unity C# Game Dev
💻

Lenovo Lookup Tool

Web tool to look up Lenovo laptop specs and warranty status by serial number. Built with vanilla JavaScript and the Lenovo API integration.

JavaScript API Integration
🗺️

A* Pathfinding Visualizer

Interactive visualization of the A* search algorithm on a grid. Lets you place obstacles and watch the algorithm find the optimal path in real time.

JavaScript Algorithms A* Search

Certifications

Formal training from top institutions in machine learning, deep learning, and AI.

Machine Learning

Stanford University
Taught by Andrew Ng — supervised/unsupervised learning, neural networks, ML best practices.

CS50's Introduction to AI with Python

Harvard University
Graph search algorithms, optimization, machine learning, neural networks, NLP.

CS50's Introduction to Computer Science

Harvard University
Core CS fundamentals: algorithms, data structures, memory, Python, SQL, JavaScript.

Deep Learning Specialization (5 Courses)

DeepLearning.AI
Neural Networks, Deep Learning, CNNs, Sequence Models, ML system design end-to-end.

Ongoing Research

Contributing to academic research in media and viewer engagement.

Apples to Apples: Viewer Retention in Long-Form vs. Short-Form Content

Ongoing Research — Computational Media Analysis
Part of an ongoing research project studying differences in viewer retention when longer content is repackaged into shorter segments. Working with the professor (first author) to collect larger, cleaner, and more granular data across a two-year period to make findings more robust. Contributing to data collection, analysis, and methodology refinement.

Ready to bring me on?

I'm actively seeking full-time ML Engineer and Data Scientist roles. Open to opportunities in computer vision, NLP, recommendation systems, or any data-driven team. Let's talk.