Jobs at NVIDIA

The role involves driving timing analysis and closure for NVIDIA's hardware, collaborating with cross-functional teams, and contributing to advanced technology projects.

Verify NVIDIA ASIC, SoC, and GPU designs, architectures, microarchitectures, memory subsystems, firmware, and hardware-software interactions. Develop verification infrastructure using reusable components, random stimulus, functional coverage, assertions, and UVM-equivalent methodologies. Collaborate with architects, designers, and software engineers while debugging complex issues. Preferred experience includes high-speed I/O, memory coherence, embedded firmware, microcontrollers, RISC-V, and verification planning.

Owns multi-generation system power and performance architecture for datacenter and high-performance platforms. Defines HSIO power management, DVFS, P-state, low-power, boot, initialization, reset, and recovery strategies across silicon, firmware, ASIC, board, and platform teams. Drives rack-scale power telemetry and platform coordination, diagnoses system-level performance and power issues, and influences roadmap and product decisions through silicon correlation and release. The role requires deep technical ownership, cross-functional authority, and experience delivering architectures across multiple silicon generations.

Develop and maintain GPU performance foundation libraries and test frameworks for Nsight tools. Implement GPU assembly tests, use emulators/simulators to validate instruction events, and document data workflows. Collaborate with hardware architecture teams to enable performance analysis and optimization of GPU-accelerated applications.

Develop and support NVIDIA networking technologies for AI clusters, including InfiniBand, NVLink, and Spectrum-X. Reproduce and root-cause complex customer issues down to source code, collaborate with R&D on fixes, analyze high-performance network metrics, and create diagnostic tools. The role requires extensive C and Python development in Linux and embedded systems, networking expertise, customer support experience, and strong communication skills. Occasional weekend or holiday support may be required.

Verify ASIC inference accelerator designs at block and SoC levels using advanced methodologies, random stimulus, functional coverage, assertions, and UVM. Develop verification infrastructure, debug designs, optimize automated flows, and collaborate with architects, designers, and pre- and post-silicon teams. Apply knowledge of ASIC design flow, power verification, DFT, netlist verification, and machine learning techniques to improve verification processes.

Architects and develops datacenter power and performance-management software, including real-time controllers, dynamic provisioning, power policies, and hardware-software interfaces. Responsibilities span architecture, pre-silicon validation, silicon bring-up, productization, deployment, and production support. The role investigates complex firmware, driver, hardware, and platform issues; develops validation automation; and collaborates with GPU, ASIC, firmware, driver, and datacenter systems teams to optimize performance, power, thermal behavior, reliability, and energy efficiency.

Architect and develop low-level GPU power and performance-management software, including P-state management, DVFS, real-time controllers, and power-management policies. Lead features through architecture, validation, silicon bring-up, productization, and deployment. Collaborate across hardware, firmware, driver, validation, and data-center teams while debugging complex system issues and developing automation for performance, power efficiency, stability, and reliability.

Design and optimize future GPU and processor memory systems for power, performance, area, and cost efficiency. Develop architecture and microarchitecture features, prototype models, and simulation workflows. Analyze benchmarks and performance or power results, debug issues across models, RTL, silicon, and systems, and collaborate with external partners. The role requires deep CPU/GPU architecture and memory systems expertise, power analysis experience, and proficiency in C, C++, and scripting languages.

Provide first-line support and troubleshooting for an HPC environment, monitor system health, triage incidents, perform maintenance and patching, and produce runbooks and documentation. Improve processes and escalate to SMEs for complex issues while supporting scheduling, compute, storage, and access concerns.

Support NVIDIA enterprise customers using GPU-accelerated platforms, triage hardware and AI/ML workload issues, collaborate with engineering teams, and drive cases through resolution. Develop support tools and products using AI, document customer interactions, and troubleshoot Linux-based multi-GPU systems, firmware, kernels, drivers, containers, and distributed workloads. The role also requires customer communication, technical analysis, and occasional weekend or holiday support.

Lead cross-functional compiler software programs from concept to delivery, coordinating global teams, tracking risks and schedules, and improving development processes. Present status to executives, drive Agile and Waterfall projects, resolve technical/resource conflicts, and implement process and tool automation to ensure timely product releases.

The Solutions Architect will evaluate server and computing solutions, coordinate qualification and certification, and support OEM relationships. Responsibilities include analyzing full-system architectures, troubleshooting schematics, diagnostics, test results, thermal and electrical data, and improving CPUs, GPUs, memory, storage, power, cooling, and interconnects. The role manages multiple technical cases, translates complex findings into recommendations, and supports AI infrastructure projects from the Round Rock area with required travel.

Serve as the senior technical contact for OEM Federal deployments of NVIDIA GPU-accelerated platforms. Own customer issues end to end, including troubleshooting, failure analysis, RMA procedures, root-cause investigation, and coordination with OEM support and NVIDIA engineering. Support secure Federal environments such as FedRAMP, IL5/IL6, and air-gapped SCIF facilities while maintaining sanitization and chain-of-custody requirements. Analyze multi-GPU systems, firmware, operating systems, networking, storage, and distributed workloads, with up to 35% travel.

Design and build intelligent compiler systems, compiler-oriented agents, code transformation workflows, and numerical verification infrastructure. Develop systems for low-level IR reasoning, code generation, optimization, differential testing, regression detection, and correctness validation across GPU-centric workloads. Collaborate with compiler, CUDA, runtime, library, and hardware teams to integrate capabilities into NVIDIA products while optimizing performance, scalability, and numerical correctness.

Develop and debug cloud-native solutions for AI/ML datacenters, focusing on Kubernetes and Slurm enhancements and customer workflows.

Develop GPU-accelerated, PyTorch-based machine learning solutions, including Graph Neural Networks, foundation models, and ensemble models. Build and optimize distributed training and inference workflows, support CUDA-X integrations, improve high-performance code, collaborate with customers and cross-functional teams, and provide technical leadership and mentorship.

Verify fabric and interconnect IP blocks and full-chip SoC integrations using SystemVerilog and UVM. Develop constrained-random and directed testbenches, create verification plans, validate DMA, routing, arbitration, ordering, flow control, and protocol compliance, and collaborate across architecture, design, software, emulation, and post-silicon teams. Drive performance, silicon, and platform verification strategies for complex interconnects and NoC subsystems.

Leads NVIDIA’s Infrastructure Security Engineering organization for EDA clusters. Builds and operates security controls across compute, storage, and networking in on-premises and multi-cloud environments while preserving performance for long-running workloads. Owns the technical roadmap, security technology lifecycle, automation, instrumentation, compliance evidence, and cross-functional execution. Develops secure-by-default infrastructure and leads teams responsible for scalable enforcement, observability, mitigation, and security outcomes.

Manage NVIDIA’s global Lenovo OEM account and drive adoption and integration of NVIDIA accelerated computing platforms. Develop technical expertise across AI hardware, networking, software, and reference architectures; identify solution opportunities; package NVIDIA technologies into Lenovo offerings; and develop co-marketing and co-selling strategies. Coordinate product, engineering, supply planning, pricing, quality, and go-to-market teams while building relationships with senior stakeholders and supporting cloud and enterprise sales channels.