Niharika D.
Graduate Research Assistant @ University of Pittsburgh
About
Portfolio: https://niharika-dwivedi.netlify.app/ I'm a Data Scientist passionate about building data-driven solutions that create real-world impact, especially in healthcare and equity-focused research. I'm currently pursuing my Master's in Data Science at the University of Pittsburgh (4.0 GPA), where I work as a Graduate Research Assistant building multimodal ML pipelines on EHR data to support clinical decision-making. My experience spans clinical ML, women's health AI, and business analytics across research labs, health tech startups, and cross-functional teams. I bring strong technical skills in Python, R and SQL paired with the ability to communicate findings clearly to both technical and non-technical audiences. Open to data analytics and ML roles in Canada , India and the US.
Canada
Vancouver
Hospital & Health Care
MySQL, Convolutional Neural Networks (CNN), Transformer Models, Healthcare Information Technology (HIT), Predictive Modeling, Medical Technology, EDA, SQL, Database Management System (DBMS), Exploratory Data Analysis, Reinforcement Learning, Amazon Web Services (AWS), Gen AI, Retrieval-Augmented Generation (RAG), Foundation Models, User-Centered Product Strategy, Data-driven Decision Making, Cross-Functional Collaboration & Leadership, Business Strategy, Customer Relationship Management (CRM)
Experience
Graduate Research Assistant
University of Pittsburgh
Conducting ML research under the supervision of Dr. Zhang at the Integrated Biostatistics and Outcome Research Lab. Developing predictive models on electronic health records to improve clinical outcomes for adult patients. Applied Python, scikit-learn, and PyTorch to build end-to-end NLP pipelines on real-world emergency department data, including fine-tuning Bio_ClinicalBERT embeddings combined with structured clinical features to predict myocardial infarction in patients.
Machine Learning Engineer
Navo Health
Singapore
Built and deployed a Transformer-based clinical risk prediction system on CTG (cardiotocography) data for early identification of fetal acidosis, aimed at improving labour outcomes. Collaborated with hospital partners to translate clinical requirements into production-ready ML pipelines, and contributed modular PyTorch implementations for rapid model benchmarking.
Data Science Researcher
The University of British Columbia
Vancouver, BC
Built and evaluated supervised learning models on 500+ anonymized student records to identify disparities in academic outcomes (AUC: 0.87). Automated data preprocessing pipelines in Python, reducing manual cleaning time by 30%, and applied SHAP analysis to generate interpretable, evidence-based policy recommendations for underrepresented groups in STEM.
Applied AI
UBC Agrobot
Vancouver, BC
Developed a computer vision pipeline for real-time grape detection in robotic harvesting systems, achieving an 87% improvement in robotic efficiency for wine production. Applied image preprocessing and feature extraction techniques to optimize performance in variable field conditions, while leading Scrum processes across a 25-member cross-functional team.
Education
University of Pittsburgh
Data Science
The University of British Columbia
Cognitive Science
Niharika D.'s Contact Information
Phone
Find the Right Leads
Find Verified Contact Data
What LeadContact does well
Find verified emails, phone numbers, and decision-makers with 98% accuracy.
Find Leads
Find the right people by company, role, industry, location, and more.
925M+ professional profiles
Find Emails
Access verified email addresses for your target contacts.
657M+ emails
Find Phone Numbers
Get cross-validated phone data from multiple top sources.
239M+ phone numbers
More Accurate. Lower Cost.
Find contact data in 1 tool with 98% accuracy
LeadContact integrates leading enrichment tools to deliver more accurate contact data—without paying for each one.
Great conversations start with the right contact.
It’s time to find yours.