Lead SoC Performance & Power Engineer

San Jose, CA · On-site$204k – $250k

About this role

About the role

As our Lead Performance architect, you'll drive the architectural configuration, system-level simulation, and PPA optimization of the chiplet by using industry-standard ESL tools and / or developing  in-house tools to integrate and calibrate highspeed I/O IPs such as PCIe, UCIe and Ethernet as well as NoC fabric into a system. You'll own the trade-off analysis that define what we tape out.

Responsibilities

  • Own PPA exploration and trade-offs between peak performance, silicon area, and thermal/power budgets, and turn that into clear tape-out recommendations.
  • Build transaction-level models (TLM) using commercial ESL suites (e.g. Platform Architect) that integrate third-party IPs such as PCIe, UCIe, and NoC etc into a full-chiplet model.
  • Define, sweep, and validate hardware configuration parameters — buffer sizes, queue depths, clock-domain crossings, routing tables — to maximize throughput and minimize latency across realistic workloads.
  • Characterize traffic across the internal NoC and the UCIe die-to-die interface to find congestion points and rule out protocol deadlocks before they reach silicon.
  • Work directly with our IP vendors to debug model/behavioral mismatches, report performance anomalies, and integrate new IP deliverables as they land.

Required

  • BS/MS in Electrical Engineering or related field with 6+ years in computer architecture, performance modeling, or microarchitecture configuration.
  • Direct, hands-on experience with commercial ESL tools such as Platform Architect, Virtualizer, or comparable frameworks.
  • Solid working knowledge of at least one of: PCIe (Gen 5/6/7), UCIe, or AMBA NoC protocols (AXI/CHI) — and a willingness to get deep on the others.
  • Strong Python for automating large-scale simulation sweeps, parsing performance reports, and analyzing results.
  • Familiarity with SystemC and transaction-level modeling paradigms — enough to write custom traffic generators when the off-the-shelf models fall short.

Nice to have

  • Fluency with power modeling or floor-planning trade-offs.
  • Prior work on a multi-die / chiplet program, or hands-on UCIe die-to-die.
  • Experience taking architectural models through to a real tape-out.

Company at a glance

AI silicon doesn't fail on compute. It fails on the infrastructure around it — power delivery, connectivity, and memory that weren't designed for the scale, speed, and packaging requirements of modern AI systems.
TYLsemi builds the chiplet infrastructure layer that solves this. Purpose-built for XPUs and Networking. Standards-based. Designed to integrate directly into your silicon program — not adapted from something else.

We're hiring across the US and India. Come build what's missing.

https://www.tylsemi.ai/company/careers/

Founded2026
Team Size11-50 employees
WorkspaceOn-site
IndustrySemiconductor Manufacturing
Location
San Jose, California, United States
Websitetylsemi.ai
LinkedInLinkedIn

Tired of cold applications?

Sign up with Clera and we'll reach out the moment a role actually fits you — no more spraying applications into the void.

Know someone who'd be great for this?