Design Verification Engineer, Tpu, Silicon Cloud

Google Google · Big Tech · Bengaluru, Karnataka, India

Design Verification Engineer for Google's TPU silicon, focusing on developing custom hardware solutions for AI and infrastructure at scale. Responsibilities include planning verification, creating verification environments using SystemVerilog and UVM, identifying coverage, debugging, and measuring coverage.

What you'd actually do

  1. Plan the verification of digital design blocks and interact with design engineers to identify important verification scenarios.
  2. Create a constrained-random verification environment using SystemVerilog and the Universal Verification Methodology (UVM).
  3. Identify and write all types of coverage measures for stimulus and corner-cases.
  4. Debug tests with design engineers to deliver functionally correct design blocks.
  5. Measure coverage to identify verification holes and to show progress towards tape-out.

Skills

Required

  • Bachelor's degree in electrical engineering, computer science, a related field, or equivalent practical experience.
  • 1 year of experience with verification methodology (e.g., Universal verification methodology (UVM)).
  • 1 year of experience in the verification of IP designs (e.g., IP, SoC, vector CPUs).
  • Experience with SystemVerilog, SVA, and functional coverage.

Nice to have

  • Master's degree or PhD in electrical engineering, computer engineering, or computer science, with a focus on computer architecture.
  • 2 years of experience with the full verification life cycle.
  • Experience in low-power design verification.
  • Experience developing and maintaining verification testbenches, test cases, and test environments.
  • Experience in artificial intelligence/machine learning (AI/ML) accelerators or vector processing units.
  • Experience with industry-standard simulators, revision control systems, and regression systems.

What the JD emphasized

  • 1 year of experience with verification methodology (e.g., Universal verification methodology (UVM)).
  • 1 year of experience in the verification of IP designs (e.g., IP, SoC, vector CPUs).
  • Experience in artificial intelligence/machine learning (AI/ML) accelerators or vector processing units.