Skip to content
View KhanUzeb's full-sized avatar
💭
God Knows What Am I doing
💭
God Knows What Am I doing
26 followers · 11 following

Achievements

Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: YOLOAchievement: Quickdraw

Block or report KhanUzeb

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
KhanUzeb/README.md

Uzeb Khan

AI Engineer • CS (Data Science) • Delhi • 20

Building intelligent systems with LLMs, Retrieval, and Machine Learning.

Portfolio Twitter LinkedIn

Visitor Count

About

I build AI systems that combine machine learning with modern LLM workflows.

Current interests:

  • Agentic AI
  • Retrieval-Augmented Generation (RAG)
  • Multi-Agent Systems
  • Deep Learning & Computer Vision
  • Inference Engineering

Tech

Languages

Python SQL C++ Go

AI

PyTorch scikit-learn Transformers OpenCV

Backend

FastAPI PostgreSQL Redis

Tools

Git Linux Docker

Activity Graph

Currently Building

Agentic AI • RAG • Multi-Agent Systems • AI Infrastructure



Currently Looking for internships and opportunities

uzebkhan898@gmail.com • https://uzebkhan.vercel.app

Pinned Loading

  1. AXIOM AXIOM Public

    Multi-agent AI system for math, physics, and chemistry problems using LangGraph orchestration with parallel specialist agents

    Python 7

  2. SIFT SIFT Public

    SIFT is an autonomous AI research agent using LLM tool calling, web search, and a dynamic reasoning loop. Built with FastAPI, Streamlit, and OpenAI-compatible APIs

    Python 3

  3. RECALL RECALL Public

    RAG system that remembers. Answers from episodic memory in ~260ms instead of ~49s. Improved Latency for answers

    Python 3

  4. KILN KILN Public

    Fine-tune LLMs on your GPU. CLI tool for QLoRA fine-tuning, DPO alignment, and eval — concurrent jobs, auto-queuing, live metrics.

    Python 2

  5. DISPATCH DISPATCH Public

    Semantic LLM router that classifies prompts into cheap/mid/hard and routes to Groq, OpenRouter, or your upstream. OpenAI/Anthropic-compatible API, MCP server, and chat demo.

    Python 1

  6. VERIS VERIS Public

    Veris: agent-agnostic local LLM evaluation and regression testing gate. Runs golden datasets against any callable, scores with DeepEval, compares rolling SQLite baselines, and returns CI-ready exit…

    Python 1