Heya! I’m Adit.
I am currently at Sandia National Labs developing geospatial machine learning models for predicting wildfire behavior. To-date I've worked in data analytics and interned in frontend software development, venture capital, and marketing. Across all that is a shared love of making thoughtfully designed products with great people, and hopefully improving the world along the way.
I recently graduated with an MS in Computer Science from Georgia Tech, specializing in Machine Learning. Prior to that, I got a BA in Economics from the University of Chicago. Outside of work, I’m a climber, photographer, national park enthusiast, and avid roadtripper. I'm lucky to have lived in 5 different states and visited 44 of them, but these days you're most likely to find me in Albuquerque, New Mexico.
Read more about me...
Read more about me...
Work Experience
Oct. 2023 - Present
- Developed algorithm using satellite imagery to map the ignition and spread of historic wildfires, enabling team to model variables that drive fire growth and rate of spread
- Created deep learning image models with CNNs (PyTorch) to classify landcover from satellite images, owning the whole process from concept to predictive model
- Supported team ML modeling tasks by building scripts in Python to pull terabytes of historic geospatial remote sensing data from Google Earth Engine
- Developed geospatial data visualizations to contextualize our work with respect to electric grid resiliency, historic wildfires, and areas with high winds near grid assets
Python
PyTorch
Google Earth Engine
QGIS
Plotly
Figma
Data Projects
Detecting Credit Card Fraud
How do you detect fraudulent credit card transactions when 99.8% of transactions aren't fraud? This page shows how I approach complex predictive modeling on an open dataset, specifically supervised machine learning on tabular data. My goal is for models to be transparent and easy to understand while maintaining strong performance.
Python
Statsmodels
sklearn
Plotly
Seaborn
Web Projects
Midway Ventures (2018)
Midway Ventures was founded in 2014 as a student organization at the University of Chicago to help VC firms identify, diligence, and source promising student startups, and to work directly with startups on projects related to fundraising and business development.
JavaScript
Bootstrap
Squarespace Dev Platform
jQuery
Greensock
HTML
LESS
Cloudy Day Club - Spotify (2020)
Cloudy Day Club is a Spotify Web Player with a splash of color for those drab cloudy days. The interface's color is personalized to the album art of whatever song you choose to listen to.
Spotify Web API
React
Redux
Express
Node.js
axios
Reach Router
Styled Components
SCSS
Heroku
Andre Castro Racing (2020)
Andre Castro is a first-generation Colombian-American racecar driver and 2020 EuroNASCAR Champion. I built Andre's website to help sponsors and racing teams better understand his potential and talent.
React
Gatsby v2
Netlify (CMS)
SASS
Bulma (CSS)
Javascript
Intel, Intelligent-Point-of-Sale (2019)
During the summer of 2019, I had the privilege of working with the amazing Technology team at Digitas in Chicago as a Front-End Software Engineering Intern. During my time at Digitas, I worked on Intel’s “Intelligent Point of Sale (IPOS)” software.
Vue
Nuxt
Git
JavaScript
JIRA/Jenkins
HTML/SCSS
Bootstrap
NVM/NPM