Physics-First AI Will Eat Electronic Hardware Design

Quilter is using AI and a deep understanding of first principles physics to tackle bottlenecks in electronic design, starting with PCB layout.

Contact

Careers

The Layout Bottlenecks End Here

Electrons obey physics, not opinions. Training AI on human layouts only repeats human mistakes and limitations. Training AI on physics—Maxwell’s equations, thermodynamics, and manufacturing constraints—creates designs that are correct by construction and reveals solutions no human would.Today, engineers still route traces by hand, the way software developers once wrote machine code. Compilers ended that era in software. Quilter ends it in hardware—turning months of layout work into minutes of computation.

This shift is inevitable. In five years, manual layout will look as outdated as punch cards. The companies that move now with physics-first AI will ship more iterations, learn faster, and turn hardware into a competitive edge.

Software teams deploy daily. Hardware teams still wait weeks for each board. This gap—the layout bottleneck—has been the last barrier holding back hardware innovation. Every delay risks missed markets, rework, and lost revenue. In today’s economy, speed wins and bottlenecks lose.

Traditional EDA built their business model around this bottleneck. We built ours on eliminating it. Physics-driven AI generates layouts that are instant, abundant, and correct by construction—no human approximation needed. Hardware teams can now iterate daily, not quarterly. What once slowed entire industries now accelerates them.

Weeks disappear from schedules

Teams explore 10–100× more design variants, moving risk and cost earlier

Engineers reclaim time

PCB designers focus on what matters most

The First Physics-Based AI Design Agent

Quilter is creating the first autonomous PCB design engine. It is not an autorouter, a co-pilot, or an LLM. It is a physics-first AI system that learns from natural law itself, not from human shortcuts. A world with Quilter is a world where boards are as plentiful and iterative as software builds, powering a new paradigm we call Hardware-Rich Development™.

Autonomous by Physics

Quilter generates complete layouts using AI trained on real-world physics and manufacturing constraints, not human examples. This lets engineers explore design spaces closed off by human intuition, surfacing solutions that would have remained undiscovered without physics-first computation.

Parallel Exploration

Dozens of layouts are generated simultaneously, each ranked for manufacturability and constraint coverage. Teams explore 100× more design variants without delay or compromise.

Continuous Verification

Physics checks are built into generation. DDR length matching, impedance control, and clearances validated during design, not after.

In five years, manual PCB design will feel like compiling code by hand.

Sergiy Nesterenko

CEO and Founder

‍Team & Culture

We build with first-principles engineering, a high bar, and respect for designers. Quilter exists so engineers spend their time inventing—not dragging traces at 2AM.

Values

Physics-first

Ownership

Learn-by-iteration

Founder & CEO — Sergiy Nesterenko

Sergiy Nesterenko founded Quilter after five years at SpaceX, where he developed electronics for Falcon 9 and Falcon Heavy and saw launches wait on boards. He created Quilter so innovation never waits on layout again.

“Bet Big, Break Rules — A Fireside with Sergiy Nesterenko”

Our People

Engineers from SpaceX, Apple, NASA, Johns Hopkins APL, and MIT. EDA builders from Cadence and Synopsys. Even operators from the 75th Rangers. We've built the tools you use and the systems that can't fail. Now we're solving with physics, not shortcuts.

Our Origins

We’re Not Chasing AI Hype

We use AI because it’s the right tool for the job, not because it’s fashionable. PCB layout is a tough, persistent bottleneck in hardware engineering. Reinforcement learning offers a real path to solving it.Our team combines deep expertise in AI, from reinforcement learning and machine learning to neural networks, with years of hands-on experience in electrical engineering. We’ve lived the same problems you have, and we’re here to fix them.