Skip to content
View zeeza18's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report zeeza18

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 supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
zeeza18/README.md

header

Typing SVG
Subtitle

Expertise

Programming Languages

Python SQL TypeScript Bash

Machine Learning & Deep Learning

PyTorch TensorFlow Keras scikit-learn XGBoost LightGBM

Large Language Models & GenAI

OpenAI Claude Gemini LangChain CrewAI Hugging Face

Cloud Platforms

AWS Azure SageMaker

DevOps & MLOps

Docker Kubernetes MLflow Airflow Git GitHub

Databases

PostgreSQL Redis Elasticsearch

Web Frameworks & APIs

FastAPI Flask Streamlit

Testing & Automation

Playwright PyTest

Data Visualization

Power BI Tableau


What I Do

AI Engineer specializing in:

Retrieval-Augmented Generation (RAG) | Large Language Models Fine-tuning
Reinforcement Learning (GRPO, PPO) | Computer Vision & Generative Models
MLOps & Production Deployment | Multi-Agent AI Systems

Current Focus:

Building Agentic AI Systems | Advancing Multi-Step Reasoning with RL
Healthcare AI & Medical Intelligence | Model Optimization & Efficient Training


Publications

IEEE

Skin Disease Analyzer with Enhancement in VGG19 Algorithm
Published in IEEE Xplore | 2024


Research Interests

Retrieval-Augmented Generation | Reinforcement Learning for LLMs | Medical AI
Computer Vision | Model Optimization | Production ML Systems


Connect With Me

LinkedIn Portfolio Email GitHub


Footer

footer

Pinned Loading

  1. EFFICIENT_TRANSFORMER EFFICIENT_TRANSFORMER Public

    Research implementation of Hierarchical Tree Attention (HTA) - an efficient transformer achieving O(N log N) complexity through recursive binary aggregation and chunkwise linear attention. 91.39% a…

    Jupyter Notebook

  2. ZEEJAI-Hyper-Chat ZEEJAI-Hyper-Chat Public

    Agentic RAG + RL pipeline that turns Qwen 2.5 7B into a multi-step reasoning agent with SFT, GRPO, and FastAPI/vLLM-powered deployment.

    Jupyter Notebook

  3. HistColoriful-Colorizing-Grayscale-Images-Using-Conditional-GANs HistColoriful-Colorizing-Grayscale-Images-Using-Conditional-GANs Public

    HistColoriful is a GAN based colorization project designed to convert grayscale images into realistic color outputs. The system includes LAB preprocessing, a UNet generator with skip connections, a…

    HTML

  4. Plane-Crasher-RL Plane-Crasher-RL Public

    Comparative study of DQN vs DDQN in a custom flying plane environment with progressive difficulty. Implements physics-based RL where agents navigate obstacles while adapting to increasing speed and…

    C

  5. SKEEZ-SKIN-DISEASE-ANALYZER SKEEZ-SKIN-DISEASE-ANALYZER Public

    This projects helps in recognizing skin diseases, along with a proper choice of medics using VGG19 algorithm with flask & React integration.

    HTML

  6. MEDICAL-RAG MEDICAL-RAG Public

    🏥 Medical RAG chatbot for nutrition information with PDF ingestion, semantic search, and citation-backed answers. Built with OpenAI, Supabase, and Next.js

    TypeScript