Skip to content
View sinjoysaha's full-sized avatar
:octocat:
Prompting the compiler in the era of vibe-coding
:octocat:
Prompting the compiler in the era of vibe-coding

Block or report sinjoysaha

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
sinjoysaha/README.md

> 👋 Hey there, I'm Sinjoy Saha


A 2nd year MS student in CSE at Penn State, where I focus on LLM training, RL and large-scale document analysis.

Sinjoy's Website Sinjoy's Linkedin Sinjoy's X Sinjoy's Scholar sinjoysaha


About me

Hello gif

🎓 MS Computer Science and Engineering at the Penn State Univeristy.

👩🏻‍💻 Interned as an SDE at Bedrock Agents, AWS on agentic workflows and tool-calling.

💼 Worked as a Senior Research Engineer at MI, Siemens Healthineers on imaging and language processing projects.

✌️ Exploring LLMs and RL.


📚 Stacks

DL Python PyTorch Transformers TRL LangChain spaCy ONNX
ML Scikit-Learn NumPy Pandas
Image OpenCV OpenSlide
Databases PostgreSQL MySQL MongoDB Milvus FAISS
Backend FastAPI Django Flask
Frontend TypeScript JavaScript React HTML CSS Bootstrap Hugo
Cloud AWS Bedrock Lambda S3 DynamoDB SQS
Dev Tools uv VSCode Git Jupyter Docker

🚀 Top Open Source Repos


All Repositories

Top Kaggle Notebooks

All Notebooks

Pinned Loading

  1. gpt2-from-scratch gpt2-from-scratch Public

    Complete reproduction of GPT-2 (124M) model and training run in PyTorch

    Jupyter Notebook 1

  2. papertrends papertrends Public

    An interactive web dashboard for exploring and visualizing research trends from paper metadata.

    JavaScript 2

  3. CSE587-midterm-project CSE587-midterm-project Public

    Midterm Project for CSE587: Deep Learing for NLP course

    Python 1

  4. llm-research llm-research Public

    Jupyter Notebook

  5. sales-analysis sales-analysis Public

    Exploratory Data Analysis of Sales dataset from an electronics store chain in the US and answering a set of real-world business questions using Python and Data Analytics

    Jupyter Notebook 28 14

  6. py-air-gestures py-air-gestures Public

    Python 1