Skip to content
View Siyalkamble's full-sized avatar
🎯
learning
🎯
learning
0 followers · 1 following

Block or report Siyalkamble

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
SiyalKamble/README.md

💫 Hi, I'm Siyal Kambale

Final-Year BSc CS Student · Building toward AI/ML Engineer (LLM / GenAI / NLP) roles

📧 siyalkamble9106@gmail.com — open to collaboration on LLM, RAG, and applied ML projects.

🌐 Portfolio: siyalkamble.vercel.app

🎯 What I'm doing

  • 🔨 Building now: Transformer from scratch + custom RAG pipeline + evaluation harness (anchor project, in progress)
  • ✅ Shipped: Classical ML projects deployed end-to-end (see below)
  • 🎯 Track: Off-campus applications to AI-native Indian startups / companies — targeting GenAI/LLM/NLP engineering roles, not generic data science.
  • 🧠 Also grinding: DSA (NeetCode-style, 150 problems), ML/DL fundamentals from scratch (NumPy → PyTorch)

🛠️ Tech Stack

Languages: Python

ML/DL: PyTorch, scikit-learn, NumPy, pandas

LLM/GenAI (in progress): Transformers, RAG, Hugging Face

Backend/Deployment: FastAPI, Streamlit, Docker, Hugging Face Spaces

Tooling/OS: Git/GitHub, uv, Linux (CachyOS/Arch), Fish shell

Python PyTorch Scikit-learn Pandas NumPy FastAPI Streamlit HuggingFace LangChain FAISS ChromaDB LoRA Docker Git GitHub Linux Jupyter VS Code RAG LLM Transformers

📈 GitHub Stats

Activity Graph

Stats Card

🌐 Connect

LinkedIn Email

Popular repositories Loading

  1. SiyalKamble SiyalKamble Public

  2. Insurance-Cost-Predictor Insurance-Cost-Predictor Public

    Compared 5 regression models (Linear, Ridge, Lasso, DecisionTree, RandomForest) with GridSearchCV to predict medical insurance charges. RandomForest best: R²=0.865.

    Jupyter Notebook

  3. Employee-Turnover Employee-Turnover Public

    Logistic regression with L1/L2 regularization to predict employee turnover. Compared baseline vs Lasso vs Ridge; L2 best at 88.5% accuracy, 0.958 ROC-AUC.

    Jupyter Notebook