# Beyond Automation: Self-Verifying AI Agents for Semiconductor and PCB Design

- Show: [EE Times Current](https://hardwarepodcasts.com/podcast/ee-times-current)
- Published: 2026-08-07
- Length: 23m
- Page: https://hardwarepodcasts.com/podcast/ee-times-current/2026-08-07-beyond-automation-self-verifying-ai-agents-for-semiconductor-and-pcb-design
- Listen: https://podcast.show/aspencore/episode/154517389/

## Summary

Amit Gupta, Chief AI Strategy Officer at Siemens EDA, and Tim Costa, VP and GM of Industrial and Computational Engineering at NVIDIA, discuss their collaboration to build self-verifying AI agents for semiconductor and PCB design. They explain how the Fuse EDA AI agent uses NVIDIA's GPU-accelerated libraries and Nemotron models to execute long-running engineering workflows while verifying outputs against physics-based EDA engines. The speakers highlight a specific case study with NVIDIA's silicon team, where the Salido characterization suite achieved a 10x reduction in turnaround time and token costs by automating manual setup and error handling. They outline three milestones for the future: workflow coverage, verified repeatability, and integration into core engineering infrastructure, aiming to cut tape-out schedules in half.

## Chapters

- [0:04](https://hardwarepodcasts.com/podcast/ee-times-current/2026-08-07-beyond-automation-self-verifying-ai-agents-for-semiconductor-and-pcb-design#t=4) Introduction: Siemens EDA and NVIDIA Collaboration
- [2:08](https://hardwarepodcasts.com/podcast/ee-times-current/2026-08-07-beyond-automation-self-verifying-ai-agents-for-semiconductor-and-pcb-design#t=128) High Stakes of AI in Semiconductor Design
- [4:31](https://hardwarepodcasts.com/podcast/ee-times-current/2026-08-07-beyond-automation-self-verifying-ai-agents-for-semiconductor-and-pcb-design#t=271) Infrastructure for Long-Running Agentic Operations
- [6:06](https://hardwarepodcasts.com/podcast/ee-times-current/2026-08-07-beyond-automation-self-verifying-ai-agents-for-semiconductor-and-pcb-design#t=366) Siemens EDA's Fuse EDA AI Agent Architecture
- [9:25](https://hardwarepodcasts.com/podcast/ee-times-current/2026-08-07-beyond-automation-self-verifying-ai-agents-for-semiconductor-and-pcb-design#t=565) NVIDIA's RIGS Framework: Reason, Improve, Govern, Scale
- [11:11](https://hardwarepodcasts.com/podcast/ee-times-current/2026-08-07-beyond-automation-self-verifying-ai-agents-for-semiconductor-and-pcb-design#t=671) Salido Characterization Suite Case Study
- [15:13](https://hardwarepodcasts.com/podcast/ee-times-current/2026-08-07-beyond-automation-self-verifying-ai-agents-for-semiconductor-and-pcb-design#t=913) Nemotron Reinforcement Learning Loop
- [16:58](https://hardwarepodcasts.com/podcast/ee-times-current/2026-08-07-beyond-automation-self-verifying-ai-agents-for-semiconductor-and-pcb-design#t=1018) Intelligence Center X and System-Level Design
- [19:25](https://hardwarepodcasts.com/podcast/ee-times-current/2026-08-07-beyond-automation-self-verifying-ai-agents-for-semiconductor-and-pcb-design#t=1165) Future Milestones: Workflow Coverage and Trusted Autonomy

## Topics

- [AI & machine learning](https://hardwarepodcasts.com/topic/ai-and-machine-learning)
- [Chips, FPGAs & semiconductors](https://hardwarepodcasts.com/topic/chips-and-fpgas)
- [PCB design & layout](https://hardwarepodcasts.com/topic/pcb-design)
- [EDA & CAD tools](https://hardwarepodcasts.com/topic/eda-and-cad-tools)
- [Scaling production](https://hardwarepodcasts.com/topic/scaling-production)

## Most relevant to

large enterprises

## Mentioned

- Siemens EDA (company)
- NVIDIA (company)
- Fuse EDA AI agent (product)
- Salido characterization suite (product)
- Nemotron (other)
- Nemo Jim (other)
- Open Shell (other)
- Intelligence Center X (product)
- CuDNN (other)
- Altair (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)
- [Solving the Hard Problems: Combining AI and Physics for PCB Design](https://hardwarepodcasts.com/podcast/moores-lobby/2026-06-23-solving-the-hard-problems-combining-ai-and-physics-for-pcb-design) (Moore's Lobby)
- [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)
- [Episode 67: A Conversation with Aart de Geus on EDA and the Future of Silicon Design](https://hardwarepodcasts.com/podcast/the-circuit/2024-05-13-episode-67-a-conversation-with-aart-de-geus-on-eda-and-the-future-of-silicon-des) (The Circuit)
- [Synopsys' Stelios Diamantidis Is Bringing the Magic of AI To Chip Design](https://hardwarepodcasts.com/podcast/moores-lobby/2023-04-04-synopsys-stelios-diamantidis-is-bringing-the-magic-of-ai-to-chip-design) (Moore's Lobby)

## Citing this page

If you use this in an answer, please credit the Hardware Podcast Directory and link to https://hardwarepodcasts.com/podcast/ee-times-current/2026-08-07-beyond-automation-self-verifying-ai-agents-for-semiconductor-and-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 EE Times Current.