Available for Data Engineering & AI/ML internships

Abhijith Aravind

Computer Science Undergraduate

Data engineering, machine learning, and AI — turning data into intelligent, real-world systems.

Abhijith Aravind

Abhijith Aravind

San Francisco Bay Area, California

Focus
Data Engineering · ML · AI
Studying
B.S. Computer Science, UC Santa Cruz
Seeking
Data Engineering & AI/ML Internships
Applied MLEnsemble ModelingData PipelinesCloud Analytics

15+

Kaggle competitions

Top 1%

Best finish · 15 / 1,908

1540

SAT score

1593

US Chess rating

Turning data into intelligent systems

Computer Science undergraduate at UC Santa Cruz with interests in machine learning, artificial intelligence, data engineering, and data science. Experienced in Python, applied ML, data pipelines, and cloud technologies through coursework, Kaggle competitions, and hands-on projects. Seeking data engineering and AI/ML internship opportunities to help build scalable, intelligent, data-driven systems.

End-to-end ML pipelines — preprocessing to evaluation
Ensemble modeling & probability calibration
Cloud-based analytics on AWS S3 & EC2
Dashboards in Tableau & Power BI

Technical toolkit

Languages

  • Python
  • Java
  • C / C++
  • SQL

Data Engineering

  • ETL / Data Pipelines
  • DuckDB
  • Data Modeling
  • Feature Engineering
  • AWS (S3, EC2)

Machine Learning

  • Scikit-learn
  • Pandas / NumPy
  • Statistical Modeling
  • Regression
  • Classification

Analytics & Visualization

  • Tableau
  • Power BI
  • Matplotlib
  • Jupyter Notebook

Live apps you can try

csv-to-duckdb

Live

Upload CSV files into a DuckDB database and run SQL queries across multiple CSV tables together in one place.

PythonDuckDBSQL

FloraVision AI

Live

Upload a photo of any plant and get a concise, AI-generated description of the flora in seconds.

PythonComputer VisionAI

AI Video Highlighter

Live

Automatically detects and surfaces the important moments in a video to speed up review and editing.

PythonMLVideo

Traffic Accident Analyzer

Live

Explores accident datasets to detect high-risk patterns and surface insights on location, time, and severity.

PythonData AnalyticsPandas

Lichess Opening Trainer

Live

A chess opening trainer that helps players drill and memorize opening lines through guided practice.

PythonChessWeb App

AppData Cleanup Assistant

Scans a Windows machine to find apps still consuming disk space via temp and AppData folders, helping reclaim storage.

PythonUtilities

More on GitHub ↗

Kaggle & applied ML

Participated in 15+ machine learning competitions involving predictive analytics, feature engineering, and ensemble modeling.

01

Top 1% — Binary Prediction of Smoker Status (15 / 1,908 teams)

Built ensemble classification pipelines with advanced feature engineering and probability calibration.

02

NeurIPS 2023 — Machine Unlearning

Explored privacy-preserving unlearning techniques balancing data-removal fidelity with retained model accuracy.

03

Google — AI Runtime Prediction

Built graph- and layout-aware regression models to predict AI compiler runtime and optimization performance.

Where I've contributed

Data Science Enthusiast · Kaggle Competitions

Feb 2023 — Present

Remote

  • Competed in 15+ ML competitions spanning predictive analytics, feature engineering, and ensemble modeling.
  • Achieved a Top 1% finish (15/1,908 teams) in a binary classification challenge.

Independent Technical Projects · GitHub · @abi1010-git

Jun 2023 — Present

Remote

  • Built csv-to-duckdb — load CSV files into a DuckDB database and query across multiple CSV tables together with SQL.
  • Created ai-flora-identifier, a web app returning AI-generated descriptions of plants from user-uploaded photos.
  • Developed ai-video-highlighter to automatically detect and surface the important moments in a video.
  • Built a traffic-accident pattern analysis project (Jupyter, Pandas) detecting high-risk patterns by location, time, and severity.
  • Created Opening-Trainer, a chess opening trainer for drilling and memorizing opening lines.
  • Built a Windows AppData cleanup assistant that scans for apps consuming disk space via temp and AppData folders.

SAT Boot Camp Tutor · Schoolhouse.world (Khan Academy Affiliate)

Jun 2023 — Sept 2024

Remote

  • Led virtual SAT sessions covering math, verbal reasoning, and test strategy, drawing on a personal 1540 score.
  • Mentored students through personalized instruction and guided practice exams.

Flight Teen Volunteer · Hiller Aviation Museum

Jun 2022 — Jun 2024

San Carlos, CA

  • Supported STEM outreach through interactive aviation and science demonstrations.
  • Facilitated visitor engagement via VR aviation experiences and invention-lab activities.

Academics & beyond

B.S. Computer Science

Sept 2024 — Present

University of California, Santa Cruz

Coursework: Data Structures & Algorithms, Computer Architecture, Probability Theory, Statistical Methods, Human-Centered AI, C Systems Programming.

Pre-College Scholars Track

Jun 2023 — Aug 2023

University of California, Berkeley

Completed undergraduate-level Probability and Statistics for Business.

Dual Enrollment

Aug 2022 — Jun 2023

Brigham Young University

College-level Calculus coursework completed during high school.

Chess

1593

Regular

1234

Quick

1710

Blitz

US Chess Federation rated player (Member ID 15930356).

Interests

  • US Chess Federation rated player
  • Basketball & team-based athletics
  • STEM mentoring & SAT tutoring

Let's build something intelligent.

Open to data engineering and AI/ML internships. Reach me on LinkedIn, or explore my code on GitHub.