Skip to content
View 22kashaf-khan's full-sized avatar
3 followers · 4 following

Highlights

  • Pro

Block or report 22kashaf-khan

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
22kashaf-khan/README.md

Hi, I'm Kashaf Purple Heart

ML / AI Engineer | LLMs · RAG · MLOps · Robotics · Berlin, Germany

LinkedIn Email Location

Winking Face About me

Hi, I'm Kashaf Purple Heart — an AI Engineer.

I work at the intersection of LLMs, RAG pipelines, and production ML with ideas with the potential to solve real problems.

  • 🏢 Currently: AI Consultant @ Siemens Mobility, Berlin
    → Driving AI adoption with LLM-powered solutions across business units

  • 🎓 M.Sc. Artificial Intelligence @ BTU Cottbus
    → Working on Humanoid Robot Training using Reinforcement Learning + Digital Twins 🤖

  • 🛠️ I love building:

    • LLM-powered agents with memory & tools
    • Retrieval-Augmented Generation (RAG) systems
    • End-to-end ML pipelines (training → deployment → monitoring)

  • 🏆 Fun fact: I won a National startup competition (NIB 2022) — presented by the President of Pakistan

 About me gif

⚡ Meet my AI Twin

Chat with Kashaf's AI Twin



Curious about what I’ve built, what I care about, or whether I think AI will take over the world?
Ask my AI twin.



Chat with my AI Twin

🔧 Tech Stack

Languages

Python SQL Bash

ML / DL Frameworks

PyTorch TensorFlow scikit-learn HuggingFace XGBoost

LLMs & GenAI

LangChain OpenAI FAISS Gemini

MLOps & Deployment

FastAPI Docker MLflow GitHub Actions

Cloud

AWS GCP Snowflake

🚀 Featured Projects

Project Description Stack

| 🤖 Multimodal AI Agent | Visual Q&A + document retrieval with memory | LLaVA · RAG · LangChain · Docker |

Open to interesting AI/ML collaborations and research discussions.
Let's connect →

Pinned Loading

  1. Scholar-Multimodal-RAG Scholar-Multimodal-RAG Public

    Production-grade RAG pipeline for scientific papers — PDF ingestion with table extraction, SSE streaming, multi-tenancy, and Weaviate vector store

    Python

  2. llm-legal-finetune llm-legal-finetune Public

    Production-grade QLoRA fine-tuning pipeline for legal & compliance LLM domain adaptation — Mistral-7B/LLaMA-3-8B, Prefect, MLflow, FastAPI, Docker

    Python