Skip to content
View YADAV1825's full-sized avatar
🔥
Unstoppable
🔥
Unstoppable

Highlights

  • Pro

Block or report YADAV1825

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
YADAV1825/README.md

Typing SVG

Rohit Portrait


  ██████╗  ██████╗ ██╗  ██╗██╗████████╗    ██╗   ██╗ █████╗ ██████╗  █████╗ ██╗   ██╗
  ██╔══██╗██╔═══██╗██║  ██║██║╚══██╔══╝    ╚██╗ ██╔╝██╔══██╗██╔══██╗██╔══██╗██║   ██║
  ██████╔╝██║   ██║███████║██║   ██║        ╚████╔╝ ███████║██║  ██║███████║██║   ██║
  ██╔══██╗██║   ██║██╔══██║██║   ██║         ╚██╔╝  ██╔══██║██║  ██║██╔══██║╚██╗ ██╔╝
 ██║  ██║╚██████╔╝██║  ██║██║   ██║          ██║   ██║  ██║██████╔╝██║  ██║ ╚████╔╝
╚═╝  ╚═╝ ╚═════╝ ╚═╝  ╚═╝╚═╝   ╚═╝          ╚═╝   ╚═╝  ╚═╝╚═════╝ ╚═╝  ╚═╝  ╚═══╝


Portfolio LinkedIn HuggingFace Email



About Me

OS VIDEO ROHIT

I'm Rohit Yadav, a 4th-year Information Technology student at NIT Jalandhar , and I don't just use tools, I build them.

I specialize in building systems end-to-end , from low-level infrastructure (bootloaders, virtual machines, compilers, operating systems) to AI/ML, genomics, and large-scale data pipelines.

🔥 What Sets Me Apart

  • 🧠 Built 25+ LLMs from scratch , 120M to 1.4B parameters on TPU clusters
  • 🔬 Trained on 500 Billion+ tokens using Google's TPU Research Cloud
  • 🏗️ Built a complete Compiler → Virtual Machine → OS pipeline from scratch
  • 🧬 Created a 500M-param DNA Foundation Model outperforming AlphaMissense & CADD
  • 💡 No frameworks, just raw memory and metal


🏅 Recognitions & Grants

Google TRC

☁️ Google TRC Grant
Awarded 320 TPU access
(SPOT + STANDARD VMs)
for large-scale LLM training & research
AMD MI300X

🔴 AMD MI300X GPU
Awarded 300 non-preemptive hours
on AMD's flagship MI300X accelerator
for high-performance AI workloads
Amazon ML

🎓 Amazon ML Summer School
Selected among 3,000 from 134,000+
applicants for Amazon's flagship
ML training program (2026)
KVPY

🔬 KVPY SA , AIR 2590
Kishore Vaigyanik Protsahan Yojana
All India Rank 2590
National Science Aptitude Fellowship
IOQM

🧮 IOQM / PRMO Awardee
Qualified Indian Olympiad Qualifier
in Mathematics (PRMO → IOQM)
National Math Olympiad pathway

💼 Experience

Role Organization Duration
🤖 AI Research Intern Molsys Pvt. Ltd. Jun 2026 – Present
🔬 Research Lead AutonomousX Apr 2026 – Present
🎓 ML Summer School Amazon (Selected: 3,000 / 134,000+ applicants) Jun 2026 – Jul 2026
🌐 Open Source Contributor Google DeepMind Gemma · Meta LLaMA Mar 2026 – Present
🖥️ Full-Stack Web Dev Intern Skylark Express Delhi Pvt Ltd (On-site, Gurugram) Jun 2025 – Jul 2025

Featured Projects


AutonomousX

AutonomousX: TPU-Native LLM Training Organization (Instinct Model Family)

AutonomousX Models Collection

AI/ML · LLMs · Transformers · Distributed Systems · JAX · TPU

  • 🏗️ Built and open-sourced 25+ LLMs (120M–1.4B params) by engineering TPU-native distributed pipelines (JAX pmap) under AutonomousX
  • 📊 Trained the Instinct model family on 500B+ tokens (PILE, DOLMA) under extreme overtraining regimes to study scaling laws, convergence, and degeneration dynamics
  • 📹 Open-sourced complete pipelines including HuggingFace weights, training logs, and a 10-minute TPU setup guide
  • 🧪 Provided a ready-to-run inference notebook for quick evaluation




RAGE-BORN: AI Terminal Agent with Autonomous Tool Execution

██████╗  █████╗  ██████╗ ███████╗    ██████╗  ██████╗ ██████╗ ███╗   ██╗
██╔══██╗██╔══██╗██╔════╝ ██╔════╝    ██╔══██╗██╔═══██╗██╔══██╗████╗  ██║
██████╔╝███████║██║  ███╗█████╗      ██████╔╝██║   ██║██████╔╝██╔██╗ ██║
██╔══██╗██╔══██║██║   ██║██╔══╝      ██╔══██╗██║   ██║██╔══██╗██║╚██╗██║
██║  ██║██║  ██║╚██████╔╝███████╗    ██████╔╝╚██████╔╝██║  ██║██║ ╚████║
╚═╝  ╚═╝╚═╝  ╚═╝ ╚═════╝ ╚══════╝    ╚═════╝  ╚═════╝ ╚═╝  ╚═╝╚═╝  ╚═══╝

RAGE BORN - AI Terminal Agent

AI Agents · LLM Systems · Terminal Automation · Browser Agents

  • 🤖 Built an AI-powered terminal agent for Linux with 25+ integrated tools enabling autonomous terminal execution, file editing, web search, browser automation, and Google Workspace operations through natural language
  • 🧠 Designed a planner → tool execution → feedback loop with persistent memory, multi-terminal sessions, background task management, and safety confirmation for destructive commands
  • 🌐 Implemented Playwright-based browser automation, persistent profiles, Google Workspace integration, and intelligent web research
  • 🔧 Engineered a production-style CLI with modular tool architecture, task history, markdown rendering, and extensible plugin design




PathoPreter

PathoPreter: Clinical-Grade SNV Pathogenicity Ranker (DNA Foundation Model)

PathoPreter - DNA Foundation Model

AI/ML · GenAI for Biology · Foundation Models · Bioinformatics

  • 🧬 Developed a hybrid genomic foundation model (500M params) fusing a Nucleotide Transformer backbone with clinical tabular features for SNV pathogenicity prediction
  • 📈 Achieved 0.9186 ROC-AUC , outperforming industry SOTA (AlphaMissense, CADD) by +0.32 ROC-AUC
  • 🏥 Designed a ranking-first clinical triage system with 75%+ pathogen recall while testing only 5–10% of variants
  • 🔍 Validated via SHAP ablation studies (64.9% reliance on raw DNA) and open-sourced the full pipeline




BroLang Stack

BroLang Compiler + Custom Virtual Machine

letbro a = 10;
letbro b = 3;
printbro(a + b);

letbro a = 10;
letbro b = 3;
printbro(a / b);   

letbro a = 10;
letbro b = 3;
printbro(a - b);

letbro a = 10;
letbro b = 3;
printbro(a * b);

ifbro (a > b) {
    printbro(999);
} elsebro {
    printbro(111);
}

ifbro (a < b) {
    printbro(222);
} elsebro {
    printbro(888); 
}

ifbro (a == b) {
    printbro(333);
} elsebro {
    printbro(777);  
}

letbro counter = 0;
whilebro (counter < 3) {
    printbro(counter);   
    letbro counter = counter + 1;
}

Systems Programming · Compilers · Runtime Systems · C++

  • 🔧 Designed a complete compiler from scratch for a custom language , implementing Lexer, Parser, AST, and Bytecode Generator
  • 💻 Built a custom 16-bit Virtual Machine (VCPU + 65KB RAM) , inspired by Java + JVM-style execution
  • ⚙️ Full runtime system: instruction decoding, stack-based execution, control flow, and I/O operations
  • 🛠️ Tech: Modern C++17, custom ISA design, bytecode architecture, manual memory management



🛠️ Tech Stack

Languages

C++ Python TypeScript JavaScript SQL

AI & Distributed Training

JAX PyTorch HuggingFace TPU GPU

Frameworks & Web

React Next.js FastAPI PostgreSQL MongoDB

Cloud & Systems

GCP AWS Docker Linux


🏆 Achievements

☁️ Google TRC Grant , 320 TPU access (SPOT + STANDARD VMs)
🔴 AMD MI300X GPU , 300 non-preemptive hours
🎓 Amazon ML Summer School 2026 , Selected among 3,000 from 134,000+ applicants
🧮 IOQM (PRMO) , Qualified for Indian Olympiad Qualifier in Mathematics   [Certificate]
🔬 KVPY SA , AIR 2590   [Certificate]
⚔️ LeetCode , Knight (2013), 600+ problems   [Profile]
CodeChef , 4-Star (1818)   [Profile]
🏅 Codeforces , Specialist (1417)   [Profile]
🥇 CodeChef START166B , Global Rank 9   [Contest]

📄 Resume


🌐 Portfolio


Rohit Portfolio Preview


📬 Contact Me

I'm always open to interesting conversations, collaborations, and opportunities!


Gmail
yrohit1825@gmail.com
LinkedIn
Rohit Yadav
GitHub
YADAV1825
HuggingFace
AutonomousX
Portfolio
rohit-portfolio
LeetCode
tomodachi_
Codeforces
tomodachi_


Profile Views



Pinned Loading

  1. BroLang-Stack BroLang-Stack Public

    I built my own compiler, that compiles programs written in my own language (BroLang), into bytecode that runs on my own virtual CPU, which executes using my own virtual machine — all from scratch i…

    C++

  2. PathoPreter PathoPreter Public

    A lightweight 500M-parameter hybrid foundation model for clinical genomic variant triage. Predicts pathogenicity from raw DNA + clinical features (conservation, gnomAD), outperforming AlphaMissense…

    Jupyter Notebook 1

  3. OS-RohitOS OS-RohitOS Public

    RohitOS v0.1 is a fully handcrafted, minimalist operating system built entirely from scratch in C and x86 Assembly, designed for 32-bit protected mode and running on bare metal or QEMU. It features…

    C

  4. AutonomousX-Instinct AutonomousX-Instinct Public

    AutonomousX Instinct is an open-source research project for end-to-end training of LLMs from scratch using JAX on Google Cloud TPU v4-8. Featuring distributed training, transparent release of check…

    Python 1

  5. Phoenix-XM Phoenix-XM Public

    Phoenix-XM is an open-source GPU architecture written in SystemVerilog featuring a pipelined Streaming Multiprocessor, warp scheduling, cache hierarchy, tensor acceleration, and a RISC-V–based inst…

    SystemVerilog

  6. RAGE-BORN RAGE-BORN Public

    An open-source AI-powered terminal agent for Linux that transforms natural language into intelligent system automation. RAGE BORN can execute terminal commands, manage files, automate browser workf…

    Python