Senior Software Development Engineer in Test

Nvidia•Santa Clara, CA

47d

About The Position

We are looking for Senior Software Development Engineer in Test to join our New GPU Integration (NPI) team for NVIDIA's Enterprise Compute SWQA team. Are you passionate about new feature development, automation development, test and validation, fix product bugs and develop test content using C/C++? Do you excel using AI tools to aid in solving complex issues? We'd love to have your skills on the team! As an engineer on this New Platform GPU Integration team, you will do many feature development that include test plan development, automate testbench independent test specification and execution workflows for worldwide chip validation teams running tests on silicon along with automation framework/infrastructure development. You will develop a system operating at large scale, running hundreds of tests per day in distributed heterogeneous servers with NVIDIA's GPUs connect to verify multiple designs/POR in many configurations those are sitting in automation farm or in cloud. You will continuously innovate and develop scalable, reliable, high performance systems and tools to enable the next generation of chips.

Requirements

BS or MS in Engineering (or equivalent experience) with 7+ years testing SW development cycle.
Solid understanding of embedded systems, Linux, Python, C and C++.
Very good knowledge of Linux and Windows packages.
Experience with Hypervisors is a big plus
Proven experience with AI tools for automation and test plan development directly applied to daily tasks. This expertise is crucial for enhancing performance, developing robust frameworks, and increasing test coverage.
Strong technical skills, with deep understanding of orchestration & automation systems, data centers and cloud architecture combined.
Solid understanding in QA methodology and pay attention to details.
Knowledge in Cluster and cluster management
Experience in developing test strategies, high quality test plans and test execution
Proficient in building test setups and fine tuning in HW and SW

Nice To Haves

Expertise in developing embedded system features, combined with solid knowledge of both software and hardware stacks.
Apply AI-powered tools to improve efficiency and quality, including test case/plan/script generation, defect detection, CBTP, bug fixing and day to day assistance
Experience with Configuration and deployment management (Ansible), Containers (Docker) and Virtualization infrastructure software (Xen, KVM)
Good understanding of C/C++ toolchain in Linux including cross-compilation (C, C++, automake/autoconf, cmake, meson).
Background with parallel programming, ideally CUDA C/C++ and OpenACC

Responsibilities

Develop test plan and orchestrate testing for Compute software releases on all new compute architecture platforms including Tesla GPUs, NVIDIA turnkey systems and OEM systems.
Develop a robust test infrastructure incorporating advanced AI tools to significantly enhance our testing capabilities and streamlining operations for more efficient and accurate results.
Improve code coverage, elevating the overall quality of our codebase and reliability of our testing processes and develop roadmaps prioritizing software development schedule for full life-cycle of tool development, test, and deployment.
Collaborate across teams to identify new features and lead developers in definition, automation implementation, and productization of those features in timely manner
Build and operate key pieces of a complete infrastructure for automation framework development, as well as, lead and develop automation support and participate in automation of manual test cases, working closely with automation infrastructure
Focus on an efficient customer experience by improving both usability and ease to attain optimal performance
Test both software functionality and internal code/structure and run regression tests for existing CUDA/Driver features.
Work in a dynamic agile software development team with very high production quality standards.