Skip to content
View sapk-pa1's full-sized avatar

Highlights

  • Pro

Block or report sapk-pa1

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
sapk-pa1/README.md

Hi 👋, I'm Pawan Sapkota Sharma

ML / AI Engineer · GenAI, RAG & Agentic Systems · Document Intelligence

Building production AI systems that turn unstructured documents into structured, reliable data.
Based in Kathmandu 🇳🇵 · M.Sc. in Computer Systems & Knowledge Engineering · Aspiring AI researcher.

GitHub followers Profile views


🚀 About Me

  • 🔭 I work on production document-intelligence pipelines — OCR/IDP, lease & financial document processing, and RAG systems.
  • 🧠 Focused on GenAI, Retrieval-Augmented Generation, agents, and fine-tuning (LoRA / QLoRA).
  • ☁️ AWS Machine Learning – Specialty certified; building on Vertex AI / Gemini, AWS Bedrock, and Qdrant.
  • 🎓 M.Sc. student at Pulchowk Campus (IOE, Tribhuvan University) — researching XAI, LLMs & low-resource (Nepali) NLP.
  • 👨‍🏫 Teaching Assistant for an AI Fellowship program.
  • 🌱 Currently going deeper into agentic RAG, eval harnesses, and Nepali NLP tokenization.
  • 💬 Ask me about RAG architectures, FastAPI in production, IDP pipelines, or ML system design.

🛠️ Languages & Tools

python   fastapi   pytorch   tensorflow   scikit-learn   pandas   numpy

GenAI & ML: LangChain · Hugging Face · Vertex AI / Gemini · AWS Bedrock · LoRA / QLoRA · DSPy Retrieval & Data: Qdrant · OpenSearch · PyMuPDF · OCR / IDP Backend: FastAPI · async SQLAlchemy · PostgreSQL · REST APIs


☁️ Platforms & DevOps

aws   docker   terraform   github actions   git   github   jupyter


🔬 Focus Areas

Area What I'm building
Document Intelligence Production OCR/IDP pipelines for lease & financial documents
RAG Systems Serverless & FastAPI-based RAG with eval harnesses and multi-provider LLM fallback
Agentic AI Agent workflows for retrieval, extraction, and reasoning
Fine-tuning LoRA / QLoRA adaptation for domain-specific tasks

📊 GitHub Stats

github stats top languages

streak stats


🐍 Contribution Snake

github contribution grid snake animation

📫 Connect with Me

linkedin email

"Let's turn data into reliable, production-grade intelligence."

Pinned Loading

  1. Aspect-Based-Sentiment-Analysis-Project Aspect-Based-Sentiment-Analysis-Project Public

    Python

  2. Credit-Score-Classification-Final Credit-Score-Classification-Final Public

    Jupyter Notebook

  3. Machine-Learning-Projects Machine-Learning-Projects Public

    Jupyter Notebook

  4. grad_from_scratch grad_from_scratch Public

    Jupyter Notebook

  5. Credit_card_final Credit_card_final Public

    Jupyter Notebook

  6. Indexing-with-pylucene Indexing-with-pylucene Public

    Jupyter Notebook