Skip to content
View harshitgavita-07's full-sized avatar
๐ŸŒด
On vacation
๐ŸŒด
On vacation

Block or report harshitgavita-07

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 donโ€™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 userโ€™s behavior. Learn more about reporting abuse.

Report abuse
harshitgavita-07/README.md
profile views ย  ย 



Typing SVG

B.Tech CSE (AI & Data Science) ยท Nxtwave Institute, Pune ยท India ๐Ÿ‡ฎ๐Ÿ‡ณ


LinkedIn Gmail GitHub


โšก Who Am I

harshit = {
    "role"       : "AI Safety Engineer | Applied AI Systems",
    "focus"      : ["Agentic AI", "Multi-agent Orchestration", "AI Evaluation", "On-device ML"],
    "building"   : ["AIOS"],
    "researching": ["PTF โ€” Agentic AI Failure Study (SSRN)", "Genesis Lock โ€” Blockchain AI Governance"],
    "philosophy" : "From math โ†’ production. No API wrappers, no shortcuts.",
    "location"   : "India ๐Ÿ‡ฎ๐Ÿ‡ณ โ€” India-first deployment always.",
}

๐Ÿ”ฌ Research In Progress

๐Ÿ“„ PTF โ€” Protection Toward Future

Empirical study of an agentic AI failure incident

An investigation into a real multi-agent system failure โ€” root cause analysis, failure cascade mapping, and safety mitigations. Submitted to SSRN.

https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6472278

#AISafety #AgenticAI #FailureAnalysis


๐Ÿš€ What I'm Building Right Now

Project What Status

| ๐Ÿ–ฅ๏ธ AIOS | Local offline AI desktop assistant + AI-Native Operating Environment โ€” zero cloud dependency | โœ… Live |


๐Ÿ† Highlight Reel

Project Signal
โšก Anthropic Performance Challenge 10.2ร— kernel speedup on Anthropic's real hiring take-home. VLIW cycles: 147K โ†’ 14K
๐Ÿง  micrograd-JAX Rebuilt Karpathy's autograd in JAX โ€” grad, jit, vmap, XLA-compiled, GPU-ready
๐Ÿ–ฅ๏ธ AIOS Local AI desktop assistant. Ollama-powered. Built before on-device AI was a trend
๐Ÿ“š ML Fundamentals 19 notebooks โ€” every core ML algorithm from scratch in NumPy. #100DaysOfML
๐Ÿญ CodeAlpha ML Internship Production ML: credit scoring, image recognition, disease prediction, speech emotion

๐Ÿ› ๏ธ Stack

Languages

Python C++ SQL

AI / ML

JAX PyTorch TensorFlow scikit-learn NumPy Ollama

Tools & Infra

VS Code Google Colab Git AWS n8n FAISS


๐Ÿ“Š GitHub Stats

GitHub Streak


๐Ÿ Contribution Snake

github contribution grid snake animation

๐Ÿ’ฌ Let's Connect

I'm actively looking for ML Engineer / Applied AI / AI Safety / AI Systems roles โ€” remote globally or India-based.

If you're building in agentic AI, multilingual NLP, on-device inference, or AI safety โ€” let's talk.

LinkedIn Email


"Build from first principles. Ship to production. Leave the APIs for later."

Pinned Loading

  1. ML_fundamentals ML_fundamentals Public

    A comprehensive guide to machine learning fundamentals including algorithms, data preprocessing, model evaluation, and practical implementations.

    Jupyter Notebook 1

  2. Anthropic_challenge-my-solution- Anthropic_challenge-my-solution- Public

    Python

  3. micrograd_JAX micrograd_JAX Public

    Forked from karpathy/micrograd

    Micrograd rebuilt with JAX - a minimal autograd engine using JAX transformations (grad, jit, vmap) for modern autodiff and accelerator-ready execution

    Jupyter Notebook

  4. Aios Aios Public

    AI-Native Operating Environment โ€” Linux-based OS with Rust kernel modules and Python AI/ML runtime. Local LLMs, multi-agent orchestration, and intent-driven computing, all on-device.

    Python 26 5

  5. paygate paygate Public

    Forked from dhruvxop19/paygate

    Cross-chain payment layer implementing HTTP 402 for AI Agent-ready API monetization with instant on-chain settlements

    TypeScript