Noopur Zambare

Noopur Zambare

M.Sc. in Computer Science, University of Alberta

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

About me

Posts

Generative AI - For Beginners

Posted:

Generative AI is transforming various industries by enabling machines to create content like images, music, and text. In this blog post, we'll explore how beginners can easily start using generative AI tools without the need for complex setups or powerful hardware.

No GPU? No Worries!

Posted:

If you’re feeling stuck because you don’t have a GPU, fear not! There are several effective alternatives that can help you run your projects smoothly. In this blog post, we'll explore two excellent options.

Detecting Poison Attacks using Neural Collapse Geometry

Posted:

There are specifically two types of Data Poison Attacks - Untargeted & Targeted. However, detecting untergetted attacks is fairly simple as the overall accuracy of the model decreases. But it becomes a problem when the attack is targeted. Until and unless, the query for that specific label/feature is not triggered, you will never understand that you are hacked! There are methods to identify Targeted Attacks but lets try to figure out if these attacks can be identified / corrected using embeddings’ representation, and thus utilising the Neural Collapse to detect poisoned labels/features.

experience

Data Science Intern

AutomationEdge | India (Remote) | Dec 2021 - Jan 2022
  • Developed and deployed an intelligent chatbot using Microsoft Bot Framework Composer integrated with Azure knowledge bases.
  • Automated FAQ resolution workflows using NLP-driven intent detection, reducing manual customer support effort.
  • Tech Stack: Microsoft Azure, Microsoft Bot Framework Composer, NLP

Machine Learning Intern

AutomationEdge | India (Remote) | Jun 2022 - Jul 2022
  • Developed and optimized text preprocessing and feature engineering pipelines to improve NLP model performance.
  • Enhanced text analytics systems, improving accuracy of customer intent recognition models.
  • Tech Stack: NLP, scikit-learn, Feature Engineering, Text Analytics

Amazon ML Summer School’22

Amazon | Apprenticeship Program | Jul 2022
  • Selected among top-performing candidates nationwide through competitive assessments in programming, logical reasoning, mathematics, and machine learning.
  • Gained hands-on exposure to Deep Neural Networks, Sequential Models, Unsupervised Learning, Causal Inference, and Reinforcement Learning.

MITACS Globalink Research Internship

University of Calgary | Calgary, Canada | May 2023 - Aug 2023
  • Developed a framework to estimate Return on Investment (ROI) of data analytics using NLP, active learning, and requirement dependency extraction techniques.
  • Designed and deployed a full-stack web application on AWS EC2 with automated CI/CD for scalable deployment.
  • Evaluated active vs passive learning strategies to improve predictive performance and model robustness in ROI estimation tasks.
  • Delivered business insights enabling better resource allocation and prioritization of data-driven initiatives under varying ROI scenarios.
  • Tech Stack: Python, NLP, Deep Learning, Machine Learning, AWS (EC2), Flask, React JS

Graduate Teaching Assistant

University of Alberta | Sep 2024 - Dec 2024
  • Served as Graduate Teaching Assistant for CMPUT 200: Ethics of Data Science and Artificial Intelligence.
  • Conducted office hours and lab sessions, supporting students with conceptual understanding and coursework challenges.
  • Evaluated assignments and exams, providing structured feedback to enhance student learning outcomes.
  • Strengthened skills in communication, time management, and collaborative academic instruction.

Project Validation

Work In Learning Opportunity | Alberta Machine Intelligence Institute | Edmonton, Canada | May 2025 - Jul 2025
  • Translated real-world business problems into well-defined machine learning problem statements and solution scopes.
  • Conducted comprehensive literature reviews and feasibility analyses to assess technical viability and implementation risks.
  • Tech Stack: Machine Learning, Research Analysis, Problem Solving, Technical Scoping

Project Validation

Work In Learning Opportunity | Alberta Machine Intelligence Institute | Edmonton, Canada | Feb 2026 - Mar 2026
  • Advised designing AI-driven multi-modal clinical decision support system solution.
  • Guided model and system selection by balancing accuracy, latency, and cost trade-offs across the ML stack.
  • Tech Stack: Transformer Models, Multimodal Learning, System Design

Research Intern (Machine Learning and Software Development Team)

Okaki Health | Remote | Mar 2026 - Jun 2026
  • Developing clinical data de-identification systems to enhance patient privacy across large-scale healthcare datasets.
  • Optimizing inference pipelines for BERT-based models to enable scalable and low-latency PHI detection and masking.
  • Tech Stack: PyTorch, Hugging Face Models, BERT, Linux

Graduate Research Assistant Fellow

Precision Health AI Research Lab, University of Alberta | May 2025 - Present
  • Used PEFT fine-tuning to design robust clinical text de-identification models using Hugging Face, Docker, and MLOps practices.
  • Built training/inference workflows on Slurm-managed HPC clusters, using CUDA multi-GPU parallelization for large-scale clinical text processing.
  • Contributed to a multi-stage document processing pipeline integrating OCR with LLM/VLM-based fallback systems for improved robustness.
  • Applied pre-trained deep learning models for medical image segmentation.
  • Built scalable ETL pipelines for large-scale clinical document ingestion, transformation, and structured data extraction.
  • Tech Stack: PyTorch, Hugging Face Transformers, Docker, LLMs, MLOps

projects

Hospital Assistant MCP Server

  • Built a multi-tool LLM agent using MCP, integrating external medical APIs, a SQL-based patient database, and an Agentic RAG pipeline (FAISS + embeddings).
  • Deployed a Streamlit-based UI with tool tracing, enabling transparent LLM decision-making.
  • Implemented patient lookup, lab analysis, and risk scoring tools for clinical decision support workflows.

RetailAgent - Agentic Retail Analytics System

  • Developed an agentic analytics system enabling natural language queries over structured Statistics Canada datasets.
  • Integrated SQLite, ChromaDB, and Gemini to support retrieval-augmented reasoning and semantic search.

Multi-Agent Medical Diagnosis Chatbot

  • Designed a multi-agent LLM chatbot for clinical diagnosis using LangChain-based orchestration.
  • Implemented vector-based patient memory using Pinecone for context-aware medical conversations.

Neaural Network Pruning Algorithm

  • Designed a Neural Collapse-inspired pruning framework to improve efficiency under data imbalance.
  • Retained effective accuracy for minority classes during pruning.
  • Achieved 95% accuracy up to 60% pruning.

Progetto - Project Management Platform

  • Built a MERN stack project management web app for university use.
  • Implemented authentication with an admin portal for CRUD operations on projects.
  • Developed RESTful APIs for creating, updating, and deleting project data.

publications