Jobs at NVIDIA

The role involves defining architecture for NVLink Fusion, collaborating with customers, mentoring teams, and managing software abstraction layers.

The role involves compiler verification through designing C++ test suites, automating testing processes, identifying gaps, and enhancing test quality using AI technologies.

Develop and implement compiler optimization algorithms for deep learning (XLA/OpenXLA) to accelerate training and inference on NVIDIA GPUs. Design graph partitioning/tensor sharding for distributed workloads, perform performance tuning and code generation using MLIR/LLVM/Triton, collaborate with framework and hardware teams, and contribute to JAX and related libraries.

Drive innovation for GPU clusters through platform management, identify gaps, develop projects, and engage with partners. Manage product roadmaps and self-service operations.

Develop advanced 3D world models by merging map and perception data to enhance autonomous vehicle navigation and safety.

The Solutions Architect will assist customers in adopting NVIDIA's GPU hardware and software, deploying AI/ML solutions, and engaging with technical teams and customers.

Design and implement compiler optimization algorithms for deep learning inference, collaborate with framework and GPU architecture teams, define public APIs, and deliver high-performance AOT and JIT compilation with reduced memory and fast build times.

Design and optimize VLM microservices for 3D reconstruction, validate model performance, and contribute to open-source projects while collaborating with teams.

As a Senior Technical Program Manager, you will lead cloud infrastructure projects, collaborating with teams to optimize AI capacity, manage operations, and ensure adherence to product lifecycles and performance indicators.

The Senior System Software Engineer will develop software tools for provisioning NVIDIA chips, coordinate tool lifecycles, and collaborate with various teams.

The role involves analyzing deep learning networks, optimizing compiler algorithms, and collaborating across teams to enhance deep learning software performance and usability.

Develop and enhance cloud infrastructure software, design APIs for automation, ensure quality through testing, and collaborate with teams for delivery.

The Senior Solutions Architect will design high-performance AI infrastructure, support sales, manage customer relationships, and provide onsite solutions and training.

As a Principal Software Engineer in the DGX Cloud team at NVIDIA, you'll lead the development of cloud systems, drive integration strategies, mentor engineers, and architect scalable automation solutions to enhance customer experiences in AI and cloud computing.

Lead the architecture and delivery of high-scale web products across frontend and backend services, mentoring engineers, and improving code quality. Collaborate to enhance AI infrastructure for efficient research management.

Lead efforts in developing and enhancing PTX Compiler infrastructure for Generative AI and Deep Learning applications in NVIDIA GPUs. Collaborate with architecture teams to support AI workloads and ensure high-quality code generation.

Design and develop real-time applications for desktop and mobile platforms, ensuring reliability and scalability. Collaborate with teams to enhance user experience and maintain code quality.

The Product Program Manager will own program execution for AI supercomputers, ensuring collaboration among cross-functional teams, managing risks, and using data-driven workflows for program insights.

Develop and enhance graphics developer tools for NVIDIA GPUs, focusing on 3D graphics, AI integration, and performance improvement. Collaborate with internal teams and manage project tasks effectively.

Develop and evaluate quantization and sparsity recipes for LLM inference, run large-scale post-training and quantization-aware experiments, build evaluation and numerics-debugging tools, collaborate with inference framework teams, and publish or upstream improvements to production inference libraries.