ART
&
TECH

Jason Lee

I graduated from UC Berkeley with a dual major in Computer Science and Art Practice, alongside the EECS Honors Program, a selective track designed to push engineers beyond the bounds of their own discipline and into broader intellectual territory.

While most of my peers stayed within one field, I was among the very few who actively bridged CS with art, two domains that rarely speak the same language. That connection became my calling.

My vision is to bridge the worlds of art and technology. I believe we are on the edge of a new realm of entertainment, one built not just on LLMs, but on deeper, less-explored fields like computer vision and reinforcement learning. The future of creative experience lies in systems that can perceive, adapt, and respond, not just generate.

Outside of work, I enjoy cooking, golf, and bouldering.

Art Practice

2021 — 2025

My Room

Acrylic on Canvas · 36″ × 48″ · 2024

An intimate exploration of personal space and memory, rendered in layered acrylic with animated light play.

Untitled

Pigments on Rice Paper · 25″ × 30″ · 2024

Exploring the tension between control and accident through water-soluble pigments on delicate rice paper.

Fire

Oil Pastel on Handmade Paper · 2024

A study in luminosity and destruction — the paradox of fire as both creator and consumer.

Untitled II

Mixed Media · 2023

Intersections of digital and physical mark-making on an unconventional substrate.

2018 — 2021

Composition I

Oil on Canvas · 2020

Early explorations in classical medium, pushing toward abstraction through form and negative space.

Composition II

Oil on Canvas · 2020

Continued study in tonal range and the geometry of shadow.

Study in Blue

Watercolor · 2019

Color theory exploration with a limited palette — the richness found within constraint.

2013 — 2018

Early Work I

Pencil on Paper · 2017

Foundational drawing studies grounded in careful observation of the physical world.

Early Work II

Charcoal · 2016

Figure drawing and tonal studies that shaped an eye for light and structure.

Machine Learning

Reinforcement Learning PyTorch OpenAI Gym

Reinforcement Learning Agent

Designed and trained a deep RL agent using policy gradient methods. The project explored reward shaping, environment design, and the challenge of sparse feedback — bridging mathematical optimization with emergent intelligent behavior. Training from scratch revealed how much architecture and hyperparameter choice govern what an agent can learn.

View Project →

Fine-Tuning LoRA Transformers

LoRA Fine-Tuning

Applied Low-Rank Adaptation (LoRA) to fine-tune a large language model on domain-specific data. Investigated the efficiency-performance tradeoff between parameter-efficient training and full fine-tuning, achieving strong results with a fraction of the compute and memory footprint — a meaningful finding for resource-constrained deployment.

View Project →