Skip to content
View pals6's full-sized avatar

Highlights

  • Pro

Block or report pals6

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.

Content in all repositories owned by your account will be closed.
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
pals6/README.md

Hi, I'm Pallavi Bichpuriya 👋

Data Engineer · Software Engineer · AI/ML Practitioner

I’m a software and data engineer with 6+ years of experience building enterprise data platforms, ETL pipelines, backend workflows, and applied AI systems.

Previously, I worked as a Senior Software Engineer at HSBC, where I improved data-processing efficiency by 40%, reduced ETL errors by 60%, and helped mitigate $4M+ in compliance risk.

I recently earned my M.S. in Computer Science from UNC Charlotte and currently contribute to multimodal AI and human-motion research at the AI4Health Center.


🔭 What I’m Working On

  • Multimodal AI systems combining text, speech, audio, and motion
  • PyTorch preprocessing and inference pipelines
  • Generative AI, VQ-VAE tokenization, and Transformer architectures
  • Scalable data pipelines, cloud platforms, and backend systems
  • Retrieval-Augmented Generation and LLM-powered applications

🚀 Featured Projects

A NotebookLM-style RAG application supporting document ingestion, vector search, citation-grounded responses, reports, quizzes, and generated content.

Tech: Python, LangChain, ChromaDB, LLM APIs, OAuth 2.0

An end-to-end ELT pipeline that transforms raw customer and order data into analytics-ready BigQuery models.

Tech: BigQuery, dbt, Apache Airflow, Terraform, SQL

An AI-powered healthcare cost-transparency platform built at Pearl Hacks 2026.

Recognition:

  • 🥉 3rd Place Overall
  • 🏆 Best Use of Solana
  • 🥈 Fidelity: Best Hack to Make Finance For All

An AI knowledge engine that processed 600+ NASA datasets for semantic search and cross-domain scientific discovery.

Tech: Python, LLMs, embeddings, knowledge graphs, data pipelines

An AI-enabled EHR assistant built over 1M+ pharmacy and formulary records to provide cost, coverage, and prior-authorization insights.

Tech: AWS, MariaDB, Next.js, LLM APIs


🛠️ Technical Skills

Languages: Python, SQL, Java, C/C++, JavaScript, Bash Data Engineering: ETL/ELT, Apache Spark, PySpark, dbt, Airflow, Data Warehousing Cloud: AWS, Google Cloud Platform, BigQuery, S3, Glue, Redshift, Athena AI/ML: PyTorch, Transformers, RAG, LangChain, ChromaDB, VQ-VAE Backend & DevOps: Flask, FastAPI, REST APIs, Docker, Kubernetes, CI/CD Databases: Oracle, DB2, BigQuery, MySQL, MariaDB Other: OpenUSD, glTF/GLB, Looker, GitHub Actions, Jenkins


🏆 Awards

  • 🥉 3rd Place Overall — Pearl Hacks 2026
  • 🏆 Best Use of Solana — Pearl Hacks 2026
  • 🥈 Best Hack to Make Finance For All — Fidelity
  • 🥉 3rd Place — CAIR Hackathon 2025
  • Star Performer — HSBC

🎓 Education

M.S. in Computer Science University of North Carolina at Charlotte GPA: 3.8/4.0


🤝 Connect With Me


Building reliable data systems and practical AI products that turn complex information into meaningful outcomes.

Pinned Loading

  1. CareLess CareLess Public

    Forked from purva115/CareLess

    A platform that gives med insurance transparency

    JavaScript 1

  2. Gen_AI_Course_Site_Spring_2026 Gen_AI_Course_Site_Spring_2026 Public

    Jupyter Notebook

  3. MentalHealthAgent MentalHealthAgent Public

    Forked from chiru-2001/MentalHealthAgent

    Python 1

  4. MMM-Flask-Server MMM-Flask-Server Public

    Python 1

  5. react react Public

    JavaScript

  6. notbooklm-clone-project notbooklm-clone-project Public

    Forked from AmeerK11/notbooklm-clone-project

    Python