Skip to content
View UdayKiranJadi's full-sized avatar
🎯
Focusing
🎯
Focusing
0 followers · 2 following

Achievements

Achievement: Pull SharkAchievement: Quickdraw

Achievements

Achievement: Pull SharkAchievement: Quickdraw

Block or report UdayKiranJadi

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
UdayKiranJadi/README.md

Hi, I'm Uday 👋

AI/ML Engineer building multi-agent systems, LLM-powered orchestration, and production-style applied AI. M.S. Computer Science, California State University Channel Islands. Active contributor to huggingface/agents-course.

LinkedIn HF Portfolio Gmail

Featured projects

Multi-Agent Power Grid Balancer — Hierarchical multi-agent system (LangGraph + LangSmith) balancing US power grid supply/demand using live EIA data. Local → regional → national coordinators mirror real grid topology; structured LLM output enforced via tool-calling, with a plain-code validation layer guaranteeing correctness. Multi-layer evals (rule-based harness, LangSmith dataset scoring, ground-truth vs. real interchange data) achieve 85% direction accuracy and 0.82 correlation against what the grid actually did. Production FastAPI service with caching, live React/Vite dashboard.

Kairos — Autonomous agentic AI system combining a PPO reinforcement learning agent with a classifier ensemble, running a closed decision loop with policy enforcement and risk controls. Event-driven pipeline (FastAPI, asyncio, Redis, PostgreSQL) with a live React dashboard.

AskMyDocs — Modular RAG application (OpenAI API, Pinecone, Sentence Transformers) for grounded document Q&A with citation-based answer generation.

OpenTutor — Open-source LLM study assistant with local inference (Hugging Face Transformers, PyTorch, Qwen2.5-0.5B-Instruct) and prompt-based task routing.

Tech stack

Python LangGraph LangSmith PyTorch TensorFlow FastAPI React PostgreSQL Docker AWS

Pinned Loading

  1. Kairos Kairos Public

    Autonomous agentic AI system combining PPO reinforcement learning with policy-controlled decision execution

    Python

  2. ask-my-docs ask-my-docs Public

    Modular RAG application for grounded document Q&A with citation-based answers

    Python

  3. open-tutor open-tutor Public

    Open-source LLM study assistant with local inference and prompt-based task routing

    Python

  4. Movie-Recommneder-System Movie-Recommneder-System Public

    Movie recommendation system built with collaborative filtering

    Jupyter Notebook

  5. CNN-Project CNN-Project Public

    CNN-based image classification system with real-time prediction interface

    Python

  6. agents-course agents-course Public

    Forked from huggingface/agents-course

    This repository contains the Hugging Face Agents Course.

    MDX