CS + Applied Math @ UC Berkeley  · 

Looq AI
Perception Software Engineering Intern (Summer 2026, current)
Building a 3D infrastructure mapping system to reconstruct real-world environments and give live feedback.

Perceive AI
Machine Learning Engineering Intern (Spring 2026)
Built end-to-end object detection pipelines for grocery SKU recognition, running 15+ experiments and designing active learning systems that reduced labeling needs by 25% across 8,000+ unlabeled frames.

BlueRobins
Full Stack Software Engineering Intern (Summer 2025)
Built full-stack features across scheduling, messaging, and dashboard workflows in Next.js, TypeScript, Supabase, FastAPI, and Flask for 500+ users, and engineered a webhook-driven backend integrating Stripe and Google Calendar to automate 100+ sessions.

SUR Lead Full Stack Mobile Developer (Fall 2024)
Rebuilt the vehicle availability system from 35,600 daily records across 100 vehicles into a clean two-table range model, and built SQL functions for calendar search, date-filtered vehicle lookup, and checkout payment validation.

Clash3D — Python, YOLO, ByteTrack, Blender A computer vision pipeline that reconstructs 2D Clash Royale screen recordings into animated 3D arena replays. Fine-tuned YOLO + ByteTrack on gameplay footage to track and classify each troop's position and identity, then rendered per-troop keyframed 3D animations in Blender via Python.

RedForce — Perplexity Hackathon · React, Express, TypeScript, SQLite A multi-agent AI security assessment tool that runs a staged adversarial attack pipeline against AI-powered products — recon, prompt extraction, data exfiltration, and privilege escalation. Streams live agent activity to a dashboard and generates an executive report with evidence and remediation steps.

English-Premier-League-Match-Predictor — Python, scikit-learn, pandas Trained Random Forest, MLP, and Decision Tree models on engineered match-level features to predict Premier League outcomes across a full 380-game season, achieving 61.5% accuracy against a 33% baseline.

Mocha — JavaScript, Chrome Extensions API A Chrome extension for tracking study sessions. Lets students log and monitor focused work time directly from their browser, keeping a running record of sessions over time.

AvoSpace — TypeScript, React A social media website where users can create profiles, post content, and browse a feed — a full-stack social platform built from scratch.

Languages

Web / Mobile

ML / Data

Backend / Infra