The opportunity
Anthropic is building custom silicon for Claude. The hardware our models run on is one of the most direct levers we have on capability, cost, and reliability — and we've decided to take design authority over it ourselves.
What you'll do
Own the integrated silicon program plan: architecture closure, RTL freeze, DV milestones, IP delivery, PD closure, DFT, tapeout, and post-silicon bring-up.
Drive external partner execution across ASIC design partners, IP vendors, foundry, and packaging/test.
Run technology and IP selection as a program: track candidate vendors and options, drive evaluations to a decision, and land the build / buy / license calls with engineering leadership.
Build the execution mechanisms a silicon team needs: milestone definitions, risk and dependency tracking, design reviews, release management, exec reporting — and keep them lightweight enough that engineers actually use them.
Manage the interface between silicon and its consumers: hardware systems for package/board/bring-up, and inference/kernels/compiler teams for hardware-software co-design, so trade-offs land as coordinated decisions rather than late surprises.
Own the post-silicon program: bring-up planning, ATE/test handoff, sample distribution, validation, and the path to production readiness.
What they're looking for
- Experience on ML accelerators, high-performance compute, networking, or other: large, high-bandwidth SoCs at advanced process nodes.
- Experience on a first-generation or early silicon program, including standing: up flows, methodology, or vendor relationships from nothing.
- Experience with both partner-executed and fully in-house programs, and a view on the trade-offs between them.
- Prior hands-on engineering background in one or more silicon domains (design, DV, PD, DFT, or SI/PI).
- Familiarity with the chip-package-system interface and co-design with a hardware systems team.
- Experience with hardware-software co-design programs: working directly with compiler, kernel, or runtime teams.
- Practical experience using AI tools in your own workflow, and clear ideas: about where they help and where they don't.
- BS/MS in EE, CE, CS, or a related field, or equivalent experience.
