Asic Physical Design Tools, Flows, Methodologies Manager

Google Google · Big Tech · Sunnyvale, CA +1

Manage and lead a team of TFM engineers responsible for the physical design flows that power Google's Tensor Processing Unit (TPU) products. This role involves guiding the team in developing, deploying, and supporting an RTL-to-GDS infrastructure, bridging design engineering and EDA capabilities, and managing priorities to ensure silicon delivery for AI/ML hardware acceleration.

What you'd actually do

  1. Manage, mentor, and grow a team of tools, flows, and methodologies (TFM) engineers supporting custom silicon development for Tensor Processing Unit (TPU) products.
  2. Oversee the physical design methodology, driving the development and optimization of flows including place and route (P&R), RC extraction, logic equivalency checking (LEC), static timing analysis (STA), EMIR, and physical verification.
  3. Triage and manage team priorities across tapeouts, balancing flow bugs, feature developments, and methodology improvements.
  4. Collaborate with internal physical design (PD) execution teams, register-transfer level (RTL) designers, and external electronic design automation (EDA) vendors to troubleshoot flow issues, improve tool quality of results (QoR), and drive vendor enhancements.
  5. Define and execute the roadmap for flow automation, runtime efficiency, and scalability across process nodes.

Skills

Required

  • Electrical Engineering, Computer Engineering, Computer Science, or related field
  • 10 years of experience with the register-transfer level (RTL)-to-GDS process and industry-standard electronic design automation (EDA) tools, including Synopsys, Cadence, and Siemens suites.
  • 6 years of experience in a people management role, managing a team of engineers within an application-specific integrated circuit (ASIC) design, semiconductor, or EDA environment.

Nice to have

  • Master's degree or PhD in Electrical Engineering, Computer Engineering or Computer Science, with an emphasis on computer architecture.
  • Experience supporting tools, flows, and methodologies (TFM) for ASICs (e.g., artificial intelligence (AI) or machine learning (ML) accelerators) on process nodes.
  • Proficiency with scripting and automation languages commonly used in EDA workflows, such as Python, Tcl, Perl, and Make.

What the JD emphasized

  • custom silicon development
  • physical design methodology
  • RTL-to-GDS process
  • EDA tools
  • people management role