Skip to content
View pallavmahajan's full-sized avatar

Block or report pallavmahajan

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
pallavmahajan/README.md

Hi, I'm Pallav Mahajan πŸ‘‹

πŸŽ“ Graduate MS in Applied Data Intelligence @ SJSU | πŸ’Ό Ex-PwC | 🧠 GenAI & Data Enthusiast πŸ“ Based in San Jose | 🌐 LinkedIn | πŸ“« Email


πŸ‘¨β€πŸ’» About Me

I bridge engineering, analytics, and business strategy shaping insights into real-world outcomes. With an MBA and an Applied Data Intelligence Master’s from San Jose State University, I specialize in:

  • Building intelligent data pipelines, AI solutions, and data analysis
  • Designing scalable, cloud-native systems
  • Applying Generative AI to business and social use cases

My work spans GenAI, big data pipelines, recommender systems, and healthcare AIβ€”always focused on outcomes, not just models.

I’m currently seeking full-time opportunities in Data Analytics, Business/Product Analytics, ML/AI, or GenAI product roles.


πŸ” Projects (Click to Explore)

πŸŽ₯ AI Text-to-Video Generator using Diffusion Models

genai-text-to-video
LoRA Β· Hugging Face Β· PyTorch Β· GCS Β· Airflow Β· Stable Diffusion

Built a prototype that turns text prompts into short videos using LoRA-finetuned diffusion models. Used GCP and Airflow for scalable prompt-to-video orchestration.


πŸ’¬ Text-to-SQL with LLM Agents

text-to-sql-llm
Mistral-7B Β· PEFT Β· SQL Β· Google BigQuery

Created a natural language interface over SQL using fine-tuned LLMs and schema-aware agents. Achieved >80% SQL generation accuracy and real-time querying.


πŸ›οΈ Amazon Recommender System for Retailers

amazon-recommendation-system
PySpark Β· ALS Β· Tableau Β· Python Β· ML

Built a personalized recommendation engine with 6M+ records, driving 20% conversion gains via clustering and sentiment analysis.


🌐 National Anthems Thematic NLP Analysis

national-anthems-nlp
Python Β· TF-IDF Β· K-Means Β· Tableau Β· Folium

Uncovered cross-cultural linguistic patterns using NLP clustering. Presented interactive maps and visuals from anthem data across 190 countries.


πŸ“° Cloud-Enabled News Trend Analytics

nyt-news-trend-analytics
GCP Β· BigQuery Β· dbt Β· Power BI

Built a cloud-based ETL and BI solution analyzing 10+ years of NYT headlines. Reduced data latency by 50%, improving media strategy and hypothesis testing.


🧰 Tech Stack Snapshot

Category Tools / Technologies
Programming Python, SQL, PySpark, R, C++
Cloud & Pipelines GCP (BigQuery, GCS), AWS (S3, Lambda), Apache Airflow, dbt
AI/ML/GenAI Hugging Face, scikit-learn, TensorFlow, LoRA, PEFT, Mistral-7B
BI & Visualization Power BI, Tableau, Excel
Other Git, Jupyter, Flask, NLP, Recommender Systems

πŸ“ˆ Focus Areas

  • 🧠 Multi-agent GenAI orchestration with cloud data
  • πŸ’¬ LLM interfaces for structured data queries
  • πŸ“¦ End-to-end ML pipelines with automated monitoring
  • 🩺 Medical imaging + vision AI for diagnostics

🀝 Let's Connect

I enjoy working on impactful tech that sits at the intersection of data, design, and decision-making. If you're building something bold in analytics or GenAI, I’d love to collaborate.

β€œI build tools to make insights faster, decisions smarter, and stories more powerful.”

Popular repositories Loading

  1. pallavmahajan pallavmahajan Public

  2. national-anthem-ml-analysis national-anthem-ml-analysis Public

    NLP and clustering analysis of world national anthems using TF-IDF, K-Means, and interactive map visualizations.

    Jupyter Notebook

  3. amazon-apparel-recommender amazon-apparel-recommender Public

    PySpark ALS recommender system for Amazon apparel reviews with sentiment analysis and a simple UI.

    Jupyter Notebook

  4. text-to-sql-GenAI text-to-sql-GenAI Public

    Natural language to SQL web app using Mistral-7B LoRA, CrewAI agents, and BigQuery for interactive analytics.

    Jupyter Notebook

  5. CineLite-Text-to-Video-Generation-using-Generative-AI CineLite-Text-to-Video-Generation-using-Generative-AI Public

    Forked from T-Dinesh-Kumar/CineLite-Text-to-Video-Generation-using-Generative-AI

    Multi-Model Text to Video Generation using Gen AI: ModelScope, CogVideoX, custom DiT pipeline, and large-scale video data on GCP.

    Jupyter Notebook

  6. nyt-archive-cloud-warehouse nyt-archive-cloud-warehouse Public

    Cloud data pipeline for New York Times archive: NYT API β†’ GCS β†’ BigQuery β†’ dbt β†’ Airflow β†’ analytics and ML.

    Jupyter Notebook