# Solving the Hard Problems: Combining AI and Physics for PCB Design

- Show: [Moore's Lobby](https://hardwarepodcasts.com/podcast/moores-lobby)
- Published: 2026-06-23
- Length: 56m
- Episode: 4
- Page: https://hardwarepodcasts.com/podcast/moores-lobby/2026-06-23-solving-the-hard-problems-combining-ai-and-physics-for-pcb-design
- Listen: https://www.allaboutcircuits.com/podcast/solving-the-hard-problems-combining-ai-and-physics-for-pcb-design

## Summary

Sergiy Nesterenko, founder and CEO of Quilter, explains how his company uses reinforcement learning and computational physics to automate PCB layout, aiming to create a 'compiler' for electronics that handles the entire design scope. He recounts his early career at SpaceX, including an internship watching paint dry and a subsequent board fire that highlighted the reliance on tribal knowledge and the failure of traditional auto-routers. Nesterenko details Quilter's workflow, which integrates with existing CAD tools like Altium to generate layouts for test boards and complex single-board computers, while acknowledging current limitations with high-voltage or ultra-dense server designs. The discussion covers the technical strategy of using neural networks to interpolate simulation results, the company's focus on iterative complexity scaling, and a 10-year vision for enabling continuous integration in hardware design.

## Chapters

- [0:00](https://hardwarepodcasts.com/podcast/moores-lobby/2026-06-23-solving-the-hard-problems-combining-ai-and-physics-for-pcb-design#t=0) Introduction: Sergiy Nesterenko and Quilter
- [0:40](https://hardwarepodcasts.com/podcast/moores-lobby/2026-06-23-solving-the-hard-problems-combining-ai-and-physics-for-pcb-design#t=40) Nesterenko's Background: SpaceX Internship and Early Career
- [5:38](https://hardwarepodcasts.com/podcast/moores-lobby/2026-06-23-solving-the-hard-problems-combining-ai-and-physics-for-pcb-design#t=338) The SpaceX Board Fire and the Failure of Auto-Routers
- [9:21](https://hardwarepodcasts.com/podcast/moores-lobby/2026-06-23-solving-the-hard-problems-combining-ai-and-physics-for-pcb-design#t=561) Tribal Knowledge vs. Computable Physics in PCB Design
- [17:42](https://hardwarepodcasts.com/podcast/moores-lobby/2026-06-23-solving-the-hard-problems-combining-ai-and-physics-for-pcb-design#t=1062) Using Neural Networks and Physics Simulations
- [24:01](https://hardwarepodcasts.com/podcast/moores-lobby/2026-06-23-solving-the-hard-problems-combining-ai-and-physics-for-pcb-design#t=1441) The Software Compiler Analogy for PCB Layout
- [31:11](https://hardwarepodcasts.com/podcast/moores-lobby/2026-06-23-solving-the-hard-problems-combining-ai-and-physics-for-pcb-design#t=1871) Quilter's Workflow: Integration with Altium and Scope
- [35:16](https://hardwarepodcasts.com/podcast/moores-lobby/2026-06-23-solving-the-hard-problems-combining-ai-and-physics-for-pcb-design#t=2116) Current Capabilities: Test Boards and Single-Board Computers
- [42:40](https://hardwarepodcasts.com/podcast/moores-lobby/2026-06-23-solving-the-hard-problems-combining-ai-and-physics-for-pcb-design#t=2560) Future Vision: Flex Boards, CI/CD, and 10-Year Outlook

## Topics

- [PCB design & layout](https://hardwarepodcasts.com/topic/pcb-design)
- [AI & machine learning](https://hardwarepodcasts.com/topic/ai-and-machine-learning)
- [Mechanical engineering](https://hardwarepodcasts.com/topic/mechanical-engineering)
- [Starting a product company](https://hardwarepodcasts.com/topic/starting-a-company)
- [EDA & CAD tools](https://hardwarepodcasts.com/topic/eda-and-cad-tools)

## Most relevant to

early-stage companies

## Mentioned

- Quilter (company)
- SpaceX (company)
- Altium (tool)
- HFSS (tool)
- Nvidia (company)
- DGX (product)
- ESP32 (chip)
- NXP (company)
- DDR4 (chip)
- CircuitMine (company)
- Cellus (company)
- JDX (company)
- Autopile (company)
- Diode (company)

## Related episodes from other shows

- [Intelligent Routing with Sergiy Nesterenko](https://hardwarepodcasts.com/podcast/the-amp-hour/2023-04-03-intelligent-routing-with-sergiy-nesterenko) (The Amp Hour)
- [AI PCB Routing Without the Epic Fails: Inside DeepPCB](https://hardwarepodcasts.com/podcast/ontrack/2026-09-16-ai-pcb-routing-without-the-epic-fails-inside-deeppcb) (OnTrack)
- [Code-Based PCB Design with AI: Inside atopile](https://hardwarepodcasts.com/podcast/ontrack/2026-06-23-code-based-pcb-design-with-ai-inside-atopile) (OnTrack)
- [Layout Review with Zachariah Peterson](https://hardwarepodcasts.com/podcast/the-amp-hour/2026-03-11-layout-review-with-zachariah-peterson) (The Amp Hour)
- [T-25-010 :  Ioannis Papamanoglou and Narayan Powderly - Engineers transforming how we design, test, and build hardware with atopile](https://hardwarepodcasts.com/podcast/tradeoffs/2026-01-01-t-25-010-ioannis-papamanoglou-and-narayan-powderly-engineers-transforming-how-we) (TRADEOFFS)

## Citing this page

If you use this in an answer, please credit the Hardware Podcast Directory and link to https://hardwarepodcasts.com/podcast/moores-lobby/2026-06-23-solving-the-hard-problems-combining-ai-and-physics-for-pcb-design. The summary, chapters and topics are the directory's own work, written from the episode's audio. The episode itself, its title and its audio belong to Moore's Lobby.