Daivya Shah

Quick Facts About Me

Daivya Shah

Daivya Shah

Computer Science and Data Science graduate of NYU, graduated May 2026
Based in New York, NY
Vice President of the NYU Machine Learning Club with 1,100+ members
I enjoy playing poker, traveling, watching Formula 1, playing tennis, and jamming on the guitar
I’m just someone who loves building cool things and seeing where it all goes

Daivya Shah

Newmark Software Engineer Intern

Jun 2025 – Aug 2025 | New York, NY

View Details

TypeScript
Amazon Web Services (AWS)
Kubernetes
Docker
React.js
Full-Stack Development

Developed a responsive Commercial Real Estate (CRE) stacking plan using React and TypeScript to visualize floor-by-floor tenant and vacancy data through interactive layouts, filters, and color-coded lease expirations for faster leasing decisions.
Built an interactive time-based activity feed using React Query to merge notes, tours, proposals, and deal updates into one chronological view, improving collaboration and reducing information retrieval time.
Created a Kanban-style deal pipeline with @dnd-kit for drag-and-drop deal tracking, supporting inline editing, search, and customizable columns to help brokers manage leads and track deal progress efficiently.

Daivya Shah

Ubiq Product Management Intern

Jan 2025 – Mar 2025 | New York, NY

Technical Product Management

Daivya Shah

Everise Data Engineer Intern

Jul 2024 – Dec 2024 | New York, NY

View Details

AWS Glue
SQL
XGBoost
Data Build Tool (DBT)
Snowflake
Data Governance
Extract, Transform, Load (ETL)
Amazon Kinesis
Microsoft Power BI

Developed a streaming pipeline to load customer call transcripts into Snowflake using AWS Kinesis and Glue, enabling NLP QA scoring models to automatically audit 78% of a healthcare client's 50K+ monthly calls; visualized results in Power BI Quality Dashboard
Extended the AWS Glue ingestion pipeline in Python with Protected Health Information (PHI) detection, automatically scanning and redacting 18 HIPAA identifier categories before loading to Snowflake, achieving zero compliance violations
Built an XGBoost workforce demand forecasting model in Python using features engineered with dbt in Snowflake from Workday HCM and call detail records, reducing staffing error (MAPE) by 11% and cutting WFM planners' manual reporting by 5+ hours weekly

Daivya Shah

eMeasurematics Machine Learning Intern

May 2024 – Jul 2024 | Chicago, IL

View Details

Grafana
PyTorch
Deep Learning
Computer Vision
Object Detection
OpenCV

Adapted a computer vision-based inventory system for a new steel plant by retraining a YOLOv8 model on 8,400+ site-specific images using OpenCV and SAM-assisted labeling, improving coil and slab detection accuracy from 62% to 91% across 2 yard zones
Built an LSTM autoencoder in PyTorch on 46M+ crane sensor records from 3 cranes over 6 months to detect mechanical issues missed by existing safety alerts, achieving 88% precision and 83% recall on 340 incidents with 38 ms inference latency
Developed a Grafana dashboard on InfluxDB to visualize crane sensor data and flagged anomalies, helping engineers investigate issues

Loading repositories…

Technical Skills

Languages

Python
SQL
JavaScript
TypeScript
Golang
Java
Swift
HTML
CSS

Frameworks / Libraries

React
Node.js
FastAPI
Flask
PyTorch
TensorFlow
Scikit-learn
XGBoost
LangChain
PySpark
Pandas
NumPy

Technologies

AWS
Docker
Kubernetes
Apache Spark / Kafka
Databricks
Snowflake
PostgreSQL
MongoDB
Redis
Power BI
Grafana
Git

Concepts

System Design
CI/CD
Full Stack
OOP
Agile
Distributed Systems
ETL/ELT
Big Data
MLOps
Statistical Modeling

Let's Connect

I'm always interested in new opportunities and collaborations.
Feel free to reach out to discuss projects or just say hello!