Skip to content
View arushahmd's full-sized avatar
  • CygnusPay
  • Lahore
  • 10:54 (UTC -12:00)

Highlights

  • Pro

Block or report arushahmd

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
arushahmd/README.md

😃 Hi, I'm Aroosh Ahmad!

AI / ML Engineer @ CygnusPay · MPhil (AI) @ PUCIT
Specialized in LLMs, NLP, Computer Vision, and MLOps

I build and deploy production-grade AI systems.

  • ⚡ LLM / RAG pipelines (data → vector DB → retriever + LLM)
  • 🛠️ Scalable deployment · MLOps · vector search
  • 🎯 Retrieval optimization · inference speed · cost reduction
  • 🚀 Hands-on with fine-tuning, hyperparameter tuning, and model serving

Open to: LLM · NLP · Computer Vision · ML Engineering roles

⚙️ Quick RAG Pipeline Example

from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from langchain.llms import OpenAI
from langchain.chains import RetrievalQA

# Load and split PDF
docs = PyPDFLoader("sample.pdf").load()
chunks = RecursiveCharacterTextSplitter(
    chunk_size=1000, chunk_overlap=200
).split_documents(docs)

# Embed + store in FAISS
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
db = FAISS.from_documents(chunks, embeddings)

# Retriever + LLM
qa = RetrievalQA.from_chain_type(
    llm=OpenAI(model="gpt-4", temperature=0),
    retriever=db.as_retriever(search_kwargs={"k": 5})
)

print(qa.run("What are the key findings in the PDF?"))

📫 Let’s Connect

Pinned Loading

  1. Business-Card-Named-Entity-Recognition Business-Card-Named-Entity-Recognition Public

    End-to-end pipeline for extracting and labeling entities from business card images with spaCy NER.

    Jupyter Notebook 1

  2. GenAI-RAG-Pdf-Bot GenAI-RAG-Pdf-Bot Public

    An AI-powered chatbot for PDF documents. Upload any PDF and interact with it using natural language queries. The system extracts text, generates embeddings, and uses Retrieval-Augmented Generation …

    Jupyter Notebook

  3. Breast-Cancer-Prediction-Flask-App Breast-Cancer-Prediction-Flask-App Public

    A simple Flask web application for breast cancer detection using a trained ML model. Users can input tumor features and get predicted probabilities for malignant or benign cases along with a clear …

    Jupyter Notebook

  4. Conversational-Flight-Assistant-Agent-RAG-Based Conversational-Flight-Assistant-Agent-RAG-Based Public

    flight assistant to get infor for flights and also visa information

    Python

  5. pose-estimation-correction-ui-emgucv pose-estimation-correction-ui-emgucv Public

    Real-time pose estimation and feedback using Emgu CV and .NET UI

    C#

  6. image-captcha-solver image-captcha-solver Public

    Jupyter Notebook