Jobs at NVIDIA

The Senior ASIC Verification Engineer will verify high-speed coherent interconnect designs, develop verification infrastructure, and ensure correctness of the designs while collaborating with various teams.

The role involves building AI inference systems, optimizing GPU performance, and developing benchmarking methodologies for large-scale deployments.

The role involves developing verification infrastructure, executing test plans, ensuring code coverage, and collaborating with design teams for post-silicon verification.

Develop AI systems for efficient inference, design and optimize kernels, and build domain-specific compilers and runtimes while collaborating with engineers.

Design and implement high-performance LLM inference systems and runtime optimizations (vLLM), profile and optimize GPU kernels, benchmark inference performance, integrate research into production-grade open-source software, and collaborate across teams to improve serving efficiency using CUDA, PyTorch, and profiling tools.

As a Networking Solutions Architect at NVIDIA, you will design and deploy AI infrastructure, optimize solutions, and collaborate with partners on high-performance networking.

Design, build, and operate large-scale security data pipelines, lake/lakehouse storage, and analytics to normalize telemetry from a massive GPU fleet. Ensure data platform security (encryption, RBAC/ABAC, audit), enable trustworthy analytics and detection, collaborate across teams to define data contracts, and maintain data quality, provenance, and freshness for security posture and automated response.

As a Senior Formal Verification Engineer, you will verify ASICs using formal methods, collaborate multi-functionally, lead methodology enhancements, and mentor junior engineers while ensuring compliance and correctness.

Drive AI-enabled ASIC development methodology by identifying cross-stage bottlenecks, building data pipelines and metrics, creating automation and AI models, mentoring engineers, and evaluating advances in AI and EDA to improve predictability, convergence, and cycle time.

The role involves optimizing neural reconstruction workflows using CUDA and PyTorch, analyzing GPU performance, and collaborating to ensure quality and performance improvements in 3D reconstruction systems.