Skip to content
View Atharva-Jayappa's full-sized avatar
🎯
Focusing
🎯
Focusing
0 followers · 1 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Highlights

  • Pro

Block or report Atharva-Jayappa

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
Atharva-Jayappa/README.md
header

About

  • 🧠 Working on agentic systems, LLM tooling, and knowledge graphs / knowledge bases — how to give models structured memory and let them act on it safely.
  • 🔌 Hands-on with MCP (Model Context Protocol), multi-agent orchestration, retrieval-augmented generation, and federated fine-tuning.
  • 🎓 Pursuing my M.S. in Computer Science at the University of Southern California.
  • 🛠️ I like building things that are useful under load — not just demos. Reliability over hype.
  • ☁️ Also comfortable with cloud (GCP / AWS) and infra when a project needs it.
  • 💬 Ask me about agent design, LLM evals, knowledge-graph backed retrieval, PyTorch, or shipping AI features safely.
status

🚀 Currently Building

🏥 ATLAS

An on-prem agentic ED operating layer built at LA Hacks 2026. Multi-agent triage and coordination for emergency departments — without sending PHI to the cloud.

TypeScript · LLM agents · healthcare

💥 blast-scope

An MCP tool that scores the blast radius of shell commands before they run — so coding agents stop nuking production by accident.

Python · MCP · agent safety

🔌 MCP_QnA

An MCP client/server pair using Gemini + tool-calling for context-grounded QA — the scaffolding for plugging structured knowledge into an agent loop.

Python · MCP · RAG

🤝 Federix

Centralized vs. federated deep-learning strategies on a shared dataset — a sandbox for studying privacy/utility trade-offs in distributed training.

Python · PyTorch · federated learning
More projects

🧰 Tech Stack

AI / Agents

Knowledge & Data

Languages

Also: AWS · GCP · Docker · Linux · Git when a project calls for it.

📍 Los Angeles, CA · Open to AI / ML / Agent Engineering internships and full-time roles for 2026.

footer

Pinned Loading

  1. atlas-lahacks atlas-lahacks Public

    ATLAS — on-prem agentic ED operating layer (LA Hacks 2026)

    TypeScript

  2. voiceysurvey voiceysurvey Public

    Forked from Manas-33/voiceysurvey

    A Voice-based AI agent designed to make data collection civic engagement accessible through a simple phone call

    TypeScript

  3. blast-scope blast-scope Public

    MCP tool that scores the blast radius of shell commands before execution.

    Python

  4. Protocol-Unmasked Protocol-Unmasked Public

    A Social Co-op Heist Game | Made for Global Game Jam USC 2026

    TypeScript 3

  5. Federix Federix Public

    A python project to implement centralized and federated deep learning strategies over a dataset

    Python

  6. MultiprogrammingOS MultiprogrammingOS Public

    An Operating System emulation that showcases essential concepts of operating systems such as process scheduling, memory management, and inter-process communication.

    C++