Senior Circuit Methodology Engineer

NVIDIA • Us, CA

1d

About The Position

NVIDIA is seeking a Senior Circuit Methodology Engineer to join their circuit design engineering team, focusing on infrastructure support for circuit design and methodology. This role involves owning and evolving the compute and GPU infrastructure in coordination with Farm, IT, CAD, and GPU infrastructure teams. The stability and management of these resources are critical for mixed-signal design and verification flows, impacting the entire circuit design department and the company's farm infrastructure. The engineer will design, develop, and maintain circuit design and verification flows on large-scale compute and GPU farms across geographies using various job schedulers. Responsibilities include monitoring farm health, identifying bottlenecks, improving throughput and utilization, bringing up new infrastructure, evaluating resources and schedulers, building automation tools, and tracking key performance metrics. User support, including debugging flow, infrastructure, and job-scheduling issues, root-cause analysis, and implementing permanent fixes, is also a key part of the role. Additionally, the engineer will develop documentation, training materials, and best-practice guidelines, and contribute to in-house AI tools for user assistance.

Requirements

• BSEE, BSCE or equivalent experience.
• Mid-level of programming skill (primarily Python and Perl).
• 8 plus years of working experience related to circuit design methodology using Cadence/Synopsys based system (Virtuoso/Custom Compiler, respectively).
• Experience with job schedulers / compute farms, primarily LSF and Slurm.
• Proven ability to debug complex multi-layer issues spanning flows, scripts, tools, and infrastructure.
• Strong communication skills and ability to partner with diverse engineering teams.

Nice To Haves

• Previous design experience is a huge plus.
• Exposure to circuit design workloads will be beneficial.

Responsibilities

• Design, develop, and maintain circuit design and verification flows that run on large-scale compute and GPU farms across geographies through various job schedulers.
• Proactively monitor farm health and job behavior, identify bottlenecks, and implement solutions to improve throughput, utilization, and turnaround time.
• Bring up and release new compute and GPU infrastructure to be used by the team.
• Evaluate and qualify new compute and GPU resources, schedulers, and related EDA infrastructure components.
• Build automation and tooling to streamline flow setup, job submission, resource allocation, logging, and reporting.
• Track important measurements (utilization, queue times, failure rates) and lead ongoing improvement projects for farm efficiency and cost effectiveness.
• Provide user support, including debugging flow, infrastructure, and job-scheduling issues.
• Perform root-cause analysis of failures and implement permanent fixes.
• Develop and maintain documentation, training materials, and best-practice guidelines for users of the circuit design compute and GPU environment.
• Proactively include information into in-house AI tools to provide first-pass user assistance.

Benefits

• Equity
• Benefits

What This Job Offers

• Job Type: Full-time
• Career Level: Senior