Physical Design Methodology Engineer, AI HW IP
TenstorrentJob Title
Physical Design Methodology Engineer, AI HW IP
Role Summary
Develop, deploy, and own the RTL-to-GDSII physical design methodology used by the IP physical design team for AI accelerators and high-performance CPU blocks. Ensure new blocks, nodes, or customer variants start from a working flow and enable repeatable PPA exploration.
This is a hybrid role based out of Toronto, ON; Austin, TX; or Belgrade, Serbia and partners closely with design teams and EDA vendors to deliver production-ready flows.
Experience Level
Mid-level (typically 5+ years of relevant experience). Candidates at various experience levels may be considered and will be assessed during the interview process.
Responsibilities
Key responsibilities include ownership of methodology, automation, and production readiness for physical design flows.
- Design, implement, and maintain RTL-to-GDSII flows and automation used in production.
- Automate repetitive steps and enable repeatable PPA (power, performance, area) exploration.
- Stand up flows for new technology nodes, PDKs, or foundry targets ahead of project needs.
- Qualify and validate new EDA tool releases and integrate vendor updates into flows.
- Implement and verify low-power intent (UPF/CPF), clock tree synthesis, and signoff flows (EM/IR, DRC/LVS).
- Partner with design teams and EDA vendors to resolve flow issues and influence tooling roadmaps.
- Document flows and procedures so production teams can run and extend them without direct support.
Requirements
Must-have technical skills and experience for immediate contribution; nice-to-have items listed where applicable.
- 5+ years developing and supporting physical design methodology or CAD flows in production use.
- Hands-on experience with industry EDA tools such as FusionCompiler/ICC2, Innovus/Genus, PrimeTime, RedHawk.
- Proficient scripting skills (Tcl, Python; Perl experience useful).
- Deep understanding of advanced-node methodology, low-power intent (UPF/CPF), clock tree synthesis, and signoff requirements (EM/IR, DRC/LVS).
- Experience standing up flows for new nodes/PDKs/foundry targets and qualifying EDA releases.
- Strong automation mindset, ability to remove manual steps and scale flows for production.
- Clear written and verbal communication; ability to document flows for handoff to teams and vendors.
- Nice-to-have: experience applying ML/LLMs for flow optimization, experience with AI accelerator or high-performance CPU physical design, and multi-variant/multi-foundry IP delivery.
Education Requirements
Not specified.
About the Company
Company: Tenstorrent
Headquarters: Austin, Texas, United States
Tenstorrent is a technology company focused on designing innovative computing solutions. They are known for their expertise in the development of advanced hardware, including ASICs and SoCs, aimed at enhancing performance and efficiency in various applications.
