Top Tech Jobs & Startup Jobs in Austin, TX

Develop GPU-accelerated techniques for generative AI training and inference, optimize algorithms and performance across NVIDIA CPU and GPU architectures, contribute to frameworks, libraries, and open-source projects, and collaborate with developers, researchers, and hardware and software engineering teams. The role focuses on LLMs, diffusion models, multimodal systems, low-level optimization, and communicating innovations through technical publications and industry conferences.

Evaluates advanced semiconductor process nodes and shapes technology choices for next-generation CPUs. Runs synthesis, place-and-route, and static timing analysis to assess power, performance, and area. Collaborates with foundries, IP developers, and hardware teams on early technology development, uses pathfinding blocks to identify implementation bottlenecks, projects node scaling, and evaluates competitive benchmarks. Develops physical-design and technology solutions to improve PPA and communicates technical trade-offs across organizations.

Design and implement GPU performance profiling tools focused on AI applications. Build features used by CUDA developers, collaborate with NVIDIA compiler and CUDA driver teams, and influence tool design. The role requires strong C++ software engineering experience, GPU hardware knowledge, and familiarity with performance tools, with preferred expertise in CUDA kernel programming, profiling, and DWARF parsing.

Develops RTL verification strategies and simulation methodologies for NVIDIA server boards and systems. Responsibilities include board and system-level RTL design, digital and analog simulation, mixed-signal model development, PCB pre-silicon verification, connectivity and timing checks, and collaboration across ASIC, FPGA, software, architecture, and system teams. The role requires extensive mixed-signal simulation or PCB design experience and Python programming skills.

Develops verification strategies, simulation methodologies, and models for board and system-level designs. Performs pre-silicon verification of PCB connectivity, design rules, and timing, while collaborating with architecture, ASIC, FPGA, software, and system teams to build end-to-end verification environments. The role requires Python, Verilog RTL, and simulation experience, with mixed-signal simulation and system validation as preferred qualifications.

Develop and optimize NVIDIA’s proprietary C++ GPU compiler backend. Responsibilities include designing compiler passes, improving code generation and machine instruction performance, supporting GPU architectures, and collaborating with compiler, hardware, and application teams. The role requires strong C++ and compiler code-generation expertise, with preferred experience in LLVM, instruction scheduling, register allocation, CUDA, DirectX, OpenGL, and Vulkan.

Design and guide security architecture for NVIDIA networking firmware and embedded subsystems. Responsibilities include threat modeling, analyzing firmware and hardware interactions, defining lifecycle security features, translating threats into requirements, partnering with hardware architects, and driving secure firmware development practices such as memory-safe C, static analysis, and fuzzing. The role requires expertise in firmware security, authorization models, cryptography, secure boot, attestation, and embedded systems.

Architect GPU power features and system-level power management solutions for NVIDIA products. Collaborate with architecture, software, ASIC design, and product teams on power strategies. Research energy-efficiency solutions across deep learning, ADAS, gaming, video playback, and idle workloads. Develop machine-learning-based power and performance models, and conduct lab measurements using specialized equipment.

Architect and develop production software for datacenter power and performance management. Responsibilities include real-time control policies, hardware-software interfaces, validation automation, silicon bring-up, debugging across firmware, drivers, hardware, and platform layers, and power optimization across racks and data halls. The role requires collaboration with GPU, ASIC, firmware, validation, and datacenter systems teams throughout the product lifecycle.

Leads engineering teams developing platform software for GPU-accelerated applications using Kubernetes, container runtimes, Kata Containers, and Confidential Containers. Responsibilities include enabling GPUs as Kubernetes resources, integrating software across NVIDIA’s technology stack, managing priorities, and delivering secure, reliable distributed systems. The role requires deep systems software expertise, engineering management experience, and hands-on knowledge of containers, Linux, cloud computing, virtualization, and confidential computing technologies.