Senior ASIC Front End Infrastructure Engineer

NVIDIA•Durham, NC

5d•$184,000 - $356,500

About The Position

NVIDIA is seeking an ASIC Infrastructure engineer to deliver the tooling and environment that enable design verification (DV) and RTL Design for its GPUs. The role supports product lines spanning consumer graphics, artificial intelligence, self-driving cars, and supercomputers. The team continuously upgrades NVIDIA’s hardware design environment so designers can work with infrastructure that operates reliably at worldwide scale and peak performance. The engineer will improve GPU front-end build flows, deploy AI toolsets and automation in secure environments, improve compute-farm technologies at cloud scale, and instrument infrastructure to measure and improve performance. The position also involves root-causing difficult infrastructure failures and transitioning teams to improved flows.

Requirements

Master’s degree in Electrical Engineering, Computer Engineering, Computer Science, or a related field, or equivalent experience.
At least 8 years of relevant work experience.
Programming proficiency in Python, Perl, or another systems programming language; object-oriented design is preferred.
Experience using AI tools for development and automation.
Experience with Make-based build systems in large, distributed computing environments.
Experience with Continuous Integration pipelines and/or pre-submit verification flows, such as Jenkins.
Tenacity in root-causing and fixing infrastructure problems, especially intermittent issues that are difficult to isolate in complex computing environments.
Verification-domain knowledge for complex ASICs or CPUs, using techniques such as random stimulus, functional coverage, and assertion-based verification methodologies.
Strong problem-solving, debugging, and analytical skills.
Good interpersonal skills and the ability and desire to work effectively as a teammate.

Responsibilities

Deploy AI toolsets at scale in secure configurations for use by hardware design teams.
Use ML, deep learning, and AI techniques to automate infrastructure work and improve design-team productivity.
Improve the speed, flexibility, and extensibility of the GPU front-end build flow.
Keep the GPU Continuous Integration system current with source-management methodologies.
Guide compute-farm, filer, and network-topology requirements at cloud scale.
Deploy and continuously improve compute-farm technologies, including containers, volume cloning, distributed storage, and distributed compute at cloud scale.
Forecast hardware-design compute-resource and EDA needs, with reporting to the CFO’s office.
Deploy tracking metrics to resolve operational issues, support forecasting, and improve design productivity.
Deploy information-security methods for hardware design.
Find and remove inefficiencies in the infrastructure.