Hardware Systems Architect jobs at Nvidia

What you’ll be doing:

• Understand, analyze, profile, and optimize AI training workloads on state-of-the-art hardware and software platforms.

• Guide development of future generations of artificial intelligence accelerators and systems.

• Develop detailed performance models and simulator infrastructure for computing systems accelerating AI training, and implement and evaluate hardware feature proposals.

• Collaborate across the company to guide the direction of machine learning at NVIDIA; spanning teams from hardware to software and research to production.

• Drive HW/SW co-design of NVIDIA’s full deep learning platform stack, from silicon to DL frameworks.

What we need to see:

• PhD in CS, EE or CSEE and 3+ years; or MS (or equivalent experience) and 6+ years of relevant work experience.

• Strong background in computer architecture, with a proven track record of architecting features in shipping high-performance processors.

• Background in artificial intelligence and large language models, in particular training algorithms and workloads.

• Experience analyzing and tuning application performance on state-of-the-art hardware.

• Experience with processor and system-level performance modelling, simulation, and evaluation before silicon exists.

• Programming skills in C++ and Python.

• Familiarity with GPU computing across all layers of the AI stack, from DL frameworks like PyTorch down to CUDA.

What you'll be doing:

• You will be contributing to power estimation models and tools for GPU products and systems like NVIDIA DGX.

• Early GPU & System Architecture exploration with focus on energy efficiency and TCO improvements at GPU and Datacenter level.

• You will help with Performance vs Power Analysis for NVIDIA future product lineup.

• Deploy machine learning techniques to develop highly accurate power and performance models of our GPUs, CPUs, Switches, and platforms.

• Understand the workload characteristics for GenAI/HPC workloads at Datacenter Scale (multi-GPU) to drive new HW/SW features for Perf@Watt improvements.

• Modeling & analysis of cutting-edge technologies like high speed & high-density interconnects.

What we need to see:

• Pursuing a MSEE/MSCE, or equivalent experience related to Power / Performance estimation and optimization techniques.

• Knowledge of energy efficient chip design fundamentals and related tradeoffs.

• Familiarity with low power design techniques such as multi-VT, Clock gating, Power gating, and Dynamic Voltage-Frequency Scaling (DVFS).

• Understanding of processors (GPU is a plus), system-SW architectures, and their performance/power modeling techniques.

• Proficiency with Python and data analysis packages like: Pandas, NumPy, PyTorch.

• Familiarity with performance monitors/simulators used in modern processor architectures.

What you’ll be doing:

• Working with Cloud Service Providers to develop and demonstrate solutions based on NVIDIA’s groundbreaking software and hardware technologies.

• Build and deploy solutions at scale using NVIDIA's AI software on cloud-based GPU platforms.

• Build custom PoCs for solutions that address customer's critical business needs while applying NVIDIA's hardware and software technologies.

• Partner with Sales Account Managers or Developer Relations Managers to identify and secure business opportunities for NVIDIA products and solutions.

• Conduct regular technical customer meetings for project/product details, feature discussions, intro to new technologies, and debugging sessions.

• Prepare and deliver technical content to customers including presentations about purpose-built solutions, workshops about NVIDIA products and solutions, etc.

What we need to see:

• BS/MS/PhD in Electrical/Computer Engineering, Computer Science, Physics, or other Engineering fields or equivalent experience.

• 7+ years of Solutions Engineering (or similar Sales Engineering roles) experience.

• Established track record of deploying AI/ ML solutions in cloud environments including AWS, GCP, Azure or OCI

• Knowledge of DevOps/MLOps technologies such as Docker/containers, Kubernetes, data center deployments, etc.

• Effective time management and capable of balancing multiple tasks.

• Ability to communicate ideas clearly through documents, presentation, etc.

Ways to stand out from the crowd:

• AWS, GCP, Azure or OCI Professional Solution Architect Certifications

• Hands-on experience with NVIDIA GPUs and SDKs (i.e. CUDA, Triton, TensorRT-LLM, etc.)

• Deep understanding of the full software development lifecycle, including best practices for system design, architectural patterns, and comprehensive testing.

• Solid working knowledge of Python

• System-level experience, specifically GPU-based systems

What you’ll be doing:

• Contribute features to vLLM that empower the newest models with the latest NVIDIA GPU hardware features; profile and optimize the inference framework (vLLM) with methods like speculative decoding,data/tensor/expert/pipeline-parallelism,prefill-decode disaggregation.

• Develop, optimize, and benchmark GPU kernels (hand-tuned and compiler-generated) using techniques such as fusion, autotuning, and memory/layout optimization; build and extend high-level DSLs and compiler infrastructure to boost kernel developer productivity while approaching peak hardware utilization.

• Define and build inference benchmarking methodologies and tools; contribute both new benchmark and NVIDIA’s submissions to the industry-leading MLPerf Inference benchmarking suite.

• Architect the scheduling and orchestration of containerized large-scale inference deployments on GPU clusters across clouds.

• Conduct and publish original research that pushes the pareto frontier for the field of ML Systems; survey recent publications and find a way to integrate research ideas and prototypes into NVIDIA’s software products.

What we need to see:

• Bachelor’s degree (or equivalent expeience) in Computer Science (CS), Computer Engineering (CE) or Software Engineering (SE) with 7+ years of experience; alternatively, Master’s degree in CS/CE/SE with 5+ years of experience; or PhD degree with the thesis and top-tier publications in ML Systems, GPU architecture, or high-performance computing.

• Strong programming skills in Python and C/C++; experience with Go or Rust is a plus; solid CS fundamentals: algorithms & data structures, operating systems, computer architecture, parallel programming, distributed systems, deep learning theories.

• Knowledgeable and passionate about performance engineering in ML frameworks (e.g., PyTorch) and inference engines (e.g., vLLM and SGLang).

• Familiarity with GPU programming and performance: CUDA, memory hierarchy, streams, NCCL; proficiency with profiling/debug tools (e.g., Nsight Systems/Compute).

• Experience with containers and orchestration (Docker, Kubernetes, Slurm); familiarity with Linux namespaces and cgroups.

• Excellent debugging, problem-solving, and communication skills; ability to excel in a fast-paced, multi-functional setting.

Ways to stand out from the crowd

• Experience building and optimizing LLM inference engines (e.g., vLLM, SGLang).

• Hands-on work with ML compilers and DSLs (e.g., Triton,TorchDynamo/Inductor,MLIR/LLVM, XLA), GPU libraries (e.g., CUTLASS) and features (e.g., CUDA Graph, Tensor Cores).

• Experience contributing tocontainerization/virtualizationtechnologies such ascontainerd/CRI-O/CRIU.

• Experience with cloud platforms (AWS/GCP/Azure), infrastructure as code, CI/CD, and production observability.

• Contributions to open-source projects and/or publications; please include links to GitHub pull requests, published papers and artifacts.

ATE/SLT hardware team provides the interface hardware of IC package testing at final test and system level test. Hardware includes highly custom high-speed sockets, active thermal plungers, and load boards. Take an active role in hardware design for both product bring-up and HVM, design and manufacture improvement, and verification/debug, to production support.

What you’ll be doing:

• Review and approve the design of test socket, thermal plunger, and other accessories related to ATE/SLT IC testing for product bring-up and production.

• Provide ATE and SLT test fixture/HW solutions from design, manufacturing order, schedule monitoring, verification, and improvement.

• Drive ATE and SLT socket/thermal technology, solutions, and qualifications.

• Drive DOE with a sense of responsibility from collecting and analyzing engineering data and making decisions and recommendations for improvement.

• Provide cross-functional support.

• Drive a project and host a meeting internal and external stakeholders.

• Apply strong hardware troubleshooting and root-cause analysis. Possess the ability to provide preventive actions.

• Able to debug ATE/SLT hardware setup such as socket, thermal plunger, PCB, chiller, and handler.

• Require on-duty lab support. Weekend support may be necessary.

What we need to see:

• Bachelor’s degree or equivalent experience is required. EE and ME related degrees are preferred.

• 5 plus years of IC testing engineering and ATE/SLT hardware engineering experience.

• Having test socket knowledge is a strong plus. Familiar with test socket mechanics, footprints, and contact pins.

• Fully capable of understanding mechanical drawings and knowing mechanical and electrical circuit knowledge.

• Have IC testing knowledge of ATE/SLT interface hardware, maintenance, troubleshooting, and repairs. (Socket, load board, thermal plungers)

• Having ATE tester knowledge is a plus.

• Proven troubleshooting skills and ability to provide solutions and prevent reoccurrence.

• Willing to conduct hands-on-work such as socket pin repair, electric wire, and tiny capacitor/resistor.

• Able to lift 30 pounds load board during unboxing, boxing, and a short transportation.

• Have the knowledge of prevention and control of electrostatic discharge (ESD)

What you'll be doing:

• Working with NVIDIA AI Native customers on data center GPU server and networking infrastructure deployments.

• Guiding customer discussions on network topologies, compute/storage, and supporting the bring-up ofserver/network/clusterdeployments.

• Identifying new project opportunities for NVIDIA products and technology solutions in data center and AI applications.

• Conducting regular technical meetings with customers as a trusted advisor, discussing product roadmaps, cluster debugging, and new technology introductions.

• Building custom demonstrations and proofs of concept to address critical business needs.

• Analyzing and debugging compute/network performance issues.

What we need to see:

• BS/MS/PhD in Electrical/Computer Engineering, Computer Science, Physics, or related fields, or equivalent experience.

• 5+ years of experience in Solution Engineering or similar roles.

• System-level understanding of server architecture, NICs, Linux, system software, and kernel drivers.

• Practical knowledge of networking - switching & routing for Ethernet/Infiniband, and data center infrastructure (power/cooling).

• Familiarity with DevOps/MLOps technologies such as Docker/containers and Kubernetes.

• Effective time management and ability to balance multiple tasks.

• Excellent communication skills for articulating ideas and code clearly through documents and presentations.

Ways to stand out from the crowd:

• External customer-facing skills and experience.

• Experience with the bring-up and deployment of large clusters.

• Proficiency in systems engineering, coding, and debugging, including C/C++, Linux kernel, and drivers.

• Hands-on experience with NVIDIA systems/SDKs (e.g., CUDA), NVIDIA networking technologies (e.g., DPU or equivalent experience, RoCE, InfiniBand), and/or ARM CPU solutions.

• Familiarity with virtualization technology concepts.

As part of the NVIDIA Solutions Architecture team, you will navigate uncharted waters and gray space to drive successful market adoption by balancing strategic alignment, data-driven analysis, and tactical execution across engineering, product, and sales teams. You will serve as a critical liaison product strategy and large-scale customer deployment.

What you’ll be doing:

• Lead the end-to-end execution for key Hyperscalers customers to optimally and rapidly go-to-market at scale with NVIDIA data center products (e.g., GB200).

• Partner with Hyperscalers Product Customer Lead to understand strategy, define metrics, ensure alignment.

• Data-Driven Execution: Collect, maintain, and analyze sophisticated data trends to assess the product's market health, identify themes, challenges, and opportunities, and guide the customer to resolution of technical roadblocks.

• Problem Solving & Navigation: Navigate complex issues effectively, embodying a productive leader who balances short-term unblocks with long-term process and product improvements.

• Executive Communication: Deliver concise, direct executive-level updates and regular status communications to multi-functional leadership on priorities, progress, and vital actions.

• Process Improvement: Integrate insights from deployment challenges and customer feedback into future developments for processes and products through close partnership with Product and Engineering teams.

What we need to see:

• BS/MS/PhD in Electrical/Computer Engineering, Computer Science, Physics, or other Engineering fields or equivalent experience.

• 8+ years of combined experience in Solutions Architecture, Technical Program Management, Product Management, System Reliability Engineer or other complex multi-functional roles.

• Proven track record to lead and influence without direct authority across technical and business functions.

• Proven analytical skills with experience in establishing benchmarks, collecting/analyzing intricate data, and redefining data into strategic themes, action items, and executive summaries.

• Skilled in reviewing logs and deployment data, and aiding customers in resolving technical concerns (e.g., identifying performance issues associated with AI/ML and system architecture).

Ways to stand out from the crowd:

• Lead multi-functional teams and influence interested parties to address challenges in customer datacenter deployments, ensuring cluster health and performance at scale.

• Established track record of driving a product from the pilot phase to at-scale deployment in a data center environment.

• Hands-on experience with NVIDIA hardware (e.g., H100, GB200) and software libraries, with an understanding of performance tuning and error diagnostics.

• Knowledge of DevOps/MLOps technologies such as Docker/containers and Kubernetes, and their relationship to data center deployments.

• Confirmed capacity to align, adopt, and disseminate insights among various internal teams (e.g., collaborating with other program leads).