Developer Technology Engineer - AI at NVIDIA

Shanghai, China

Apply Now

Not SpecifiedCompensation

Mid-level (3 to 4 years)Experience Level

Full TimeJob Type

UnknownVisa

AI, High Performance Computing, Machine LearningIndustries

Requirements

A degree from university in an engineering or computer science related discipline (BS; MS or PhD preferred)
2+ years of working experience
Strong knowledge of C/C++ and/or Fortran
Deep knowledge of software design, programming techniques, and algorithms
Expert knowledge of LLM training/inference optimization, including development and optimization experience in distributed training/inference, NCCL, NVSHMEM, IB, RoCE, etc
Strong mathematical fundamentals, including linear algebra and numerical methods
Experience with parallel programming, ideally CUDA C/C++ and OpenACC
Good communication and organization skills, with a logical approach to problem solving, good time management, and task prioritization skills

Responsibilities

Work directly with key application developers (especially LLM) to understand current and future problems, create and optimize core parallel algorithms and data structures for GPU solutions via library development and direct application contributions, including training and inference optimization for large language models and contributions to frameworks like Megatron, TRTLLM, SGLang, vLLM
Collaborate closely with NVIDIA's architecture, research, libraries, tools, and system software teams to influence next-generation architectures, software platforms, and programming models by investigating impact on application performance and developer productivity
Engage in deep optimization of high-performance operators, including CUDA deep optimization, instruction and compiler optimization, supporting customers or integrating into products like cuDNN, cuBLAS, and CUTLASS
Perform in-depth analysis and optimization to ensure best performance on current- and next-generation GPU architectures in machine/deep learning, scientific computing, and data processing
Travel for conferences and on-site visits with developers

Skills

Key technologies and capabilities for this role

C/C++FortranCUDAGPULLMMegatronTRTLLMSGLangvLLMcuDNNcuBLASCUTLASSparallel algorithmsdeep learning

Questions & Answers

Common questions about this position

What education and experience are required for this Developer Technology Engineer role?

A degree from university in an engineering or computer science related discipline (BS; MS or PhD preferred) is required, along with 2+ years of working experience.

What key technical skills are needed for this position?

Strong knowledge of C/C++ and/or Fortran, deep knowledge of software design, programming techniques, and algorithms, expert knowledge of LLM training/inference optimization (including distributed training/inference, NCCL, NVSHMEM, IB, RoCE), strong mathematical fundamentals, and experience with parallel programming like CUDA C/C++ and OpenACC are required.

What is the compensation like at NVIDIA for this role?

NVIDIA offers highly competitive salaries and a comprehensive benefits package.

Is this a remote position, or is travel required?

This information is not specified in the job description regarding remote or office policy, but some travel is required for conferences and on-site visits with developers.

What makes a strong candidate for this NVIDIA DevTech role?

NVIDIA seeks a creative and autonomous computer scientist with a genuine passion for parallel computing, along with good communication, organization skills, logical problem-solving, time management, and task prioritization.

NVIDIA

Designs GPUs and AI computing solutions

About NVIDIA

NVIDIA designs and manufactures graphics processing units (GPUs) and system on a chip units (SoCs) for various markets, including gaming, professional visualization, data centers, and automotive. Their products include GPUs tailored for gaming and professional use, as well as platforms for artificial intelligence (AI) and high-performance computing (HPC) that cater to developers, data scientists, and IT administrators. NVIDIA generates revenue through the sale of hardware, software solutions, and cloud-based services, such as NVIDIA CloudXR and NGC, which enhance experiences in AI, machine learning, and computer vision. What sets NVIDIA apart from competitors is its strong focus on research and development, allowing it to maintain a leadership position in a competitive market. The company's goal is to drive innovation and provide advanced solutions that meet the needs of a diverse clientele, including gamers, researchers, and enterprises.

Santa Clara, CaliforniaHeadquarters

1993Year Founded

$19.5MTotal Funding

IPOCompany Stage

Automotive & Transportation, Enterprise Software, AI & Machine Learning, GamingIndustries

10,001+Employees

Benefits

Company Equity

401(k) Company Match

Risks

Increased competition from AI startups like xAI could challenge NVIDIA's market position.

Serve Robotics' expansion may divert resources from NVIDIA's core GPU and AI businesses.

Integration of VinBrain may pose challenges and distract from NVIDIA's primary operations.

Differentiation

NVIDIA leads in AI and HPC solutions with cutting-edge GPU technology.

The company excels in diverse markets, including gaming, data centers, and autonomous vehicles.

NVIDIA's cloud services, like CloudXR, offer scalable solutions for AI and machine learning.

Upsides

Acquisition of VinBrain enhances NVIDIA's AI capabilities in the healthcare sector.

Investment in Nebius Group boosts NVIDIA's AI infrastructure and cloud platform offerings.

Serve Robotics' expansion, backed by NVIDIA, highlights growth in autonomous delivery services.

Land your dream remote job 3x faster with AI

Try Jobo Free