Skip to content
View AnvitDevadiga's full-sized avatar
1 follower · 0 following
  • Mumbai, India

Achievements

Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: QuickdrawAchievement: YOLO

Block or report AnvitDevadiga

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.

Content in all repositories owned by your account will be closed.
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
AnvitDevadiga/README.md

Anvit Devadiga

AI Engineer | ML Systems & Agentic AI

I build AI systems focused on model performance, reliable agents, and backend infrastructure.

Featured Projects

  • MiniLM Lab — Transformer training, inference optimization, and reproducible benchmarks.
  • Tender — Coding agent infrastructure with isolated execution, independent verification, and evaluation.

Tech Stack

  • Languages: Python, TypeScript, SQL
  • AI/ML: PyTorch, Transformers, LangGraph, MCP, RAG
  • Backend & Infrastructure: FastAPI, PostgreSQL, SQLite, Docker

Connect

Email

Pinned Loading

  1. MiniLM-Lab MiniLM-Lab Public

    A from-scratch Mini-LLM lab: train, evaluate, and benchmark Transformer components on Apple Silicon.

    Python

  2. Tender Tender Public

    Python

  3. trycua/cua trycua/cua Public

    Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.

    Rust 30.9k 2.2k

  4. openai/openai-agents-python openai/openai-agents-python Public

    A lightweight, powerful framework for multi-agent workflows

    Python 30.3k 4.9k