Skip to content
View taljindergill78's full-sized avatar

Block or report taljindergill78

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
taljindergill78/README.md

πŸ‘‹ Hi, I'm Taljinder Singh

Master's Student in Data Science @ Arizona State University (Class of 2026) 🧠 Machine Learning Β· NLP Β· GenAI Systems Β· IIT Roorkee πŸ“ Tempe, Arizona Β· πŸ”Ž Actively seeking Full-Time DS / ML / AI roles

LinkedIn Portfolio Email


πŸ’‘ About Me

I'm a data scientist in training with a passion for turning real-world complexity into structured, actionable insights.

My journey began at IIT Roorkee, where I built a strong foundation in analytical thinking. Since then, I've worked on pricing models, time series forecasting, and financial analytics at the enterprise level, learning how to use data to solve high-stakes business problems.

At Arizona State University, my focus is on machine learning, big data systems, and building personalized AI agents that adapt to human behavior. I enjoy work that blends statistical modeling, practical intuition, and clean execution.

If it involves messy data, thoughtful modeling, and clear storytelling β€” I'm all in.


πŸ› οΈ Tech Stack

Programming & Databases

Python SQL PostgreSQL

Data & Machine Learning

Pandas NumPy Scikit-learn TensorFlow Apache Spark

NLP & LLM Systems

HuggingFace LangChain PyTorch

Cloud & MLOps

AWS Docker Git Tableau


πŸš€ Featured Projects

End-to-end retail sales forecasting pipeline with DVC, MLflow, AWS (RDS, Glue, SageMaker, EKS), Docker, and CI/CD. Tree-based models: LightGBM, XGBoost, CatBoost.

MLOps AWS Docker MLflow LightGBM

Fine-tuned LLMs (LLAMA2, LLAMA3.2, Mistral-7B) for personalized recipe generation using QLoRA. Achieved 96% precision and BLEU 0.52.

LLM Fine-tuning QLoRA HuggingFace Transformers

Capstone project β€” end-to-end data science and machine learning system for open-source intelligence investigation and analysis.

Capstone Python ML Data Science

AI-powered memory assistant built during a hackathon. Features retention tracking, semantic memory, and proactive learning insights.

Hackathon TypeScript AI Agents LLM

NLP-based text classification using TF-IDF, linear models, and ensemble techniques β€” with systematic evaluation to identify real disaster tweets.

NLP Scikit-learn TF-IDF Ensemble

Analyzed 150K+ Yelp reviews to extract insights about Arizona restaurants and user behavior using Apache Spark and PySpark for distributed processing.

Big Data PySpark Spark Data Engineering


πŸ“Š GitHub Stats

GitHub Streak
Profile Details

🐍 Watch the Snake Eat My Contributions

github-snake

πŸ“¬ Let's Connect

I'm always open to conversations about ML, AI research, data-driven products, and full-time opportunities in Data Science Β· ML Engineering Β· AI Engineering.

LinkedIn

Pinned Loading

  1. retail-forecasting retail-forecasting Public

    End-to-end retail sales forecasting with MLOps: DVC pipelines, MLflow tracking & registry, AWS (RDS, Glue, SageMaker, EKS), Docker, and CI/CD. Tree-based models (LightGBM, XGBoost, CatBoost).

    Python

  2. osint-investigation-swarm osint-investigation-swarm Public

    Capstone project repository for end to end data science and machine learning development.

    Python 1

  3. Rewind Rewind Public

    Forked from SankrityaT/Rewind

    AI-powered memory assistant built during a hackathon, focusing on retention tracking, semantic memory, and proactive learning insights.

    TypeScript

  4. yelp-arizona-analysis yelp-arizona-analysis Public

    This project analyzes the Yelp dataset for the state of Arizona to extract insights about restaurant businesses and user behavior. Using Apache Spark and PySpark for distributed data processing, th…

    Jupyter Notebook

  5. disaster-tweets-classification disaster-tweets-classification Public

    NLP-based classification of disaster-related tweets using TF-IDF features, linear models, and ensemble techniques, with systematic evaluation and performance tuning.

    Jupyter Notebook

  6. book-recommender-system book-recommender-system Public

    A personalized book recommender system that suggests books to users based on their reading preferences and past ratings, using collaborative filtering techniques on the Book Crossing dataset.

    Jupyter Notebook