обновлено 22 часа назад
Platform Power Thermal Performance Engineer (AI Infrastructure)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Platform Power Thermal Performance Engineer (AI Infrastructure): Validating and optimizing performance for AI server platforms across CPU hosts, GPU I/O, memory, storage, and networking with an accent on benchmark execution, topology validation, and system-level analysis. Focus on debugging performance bottlenecks, automating experiments, and supporting scale-up and scale-out platform optimization.
Location: On-site in Shanghai, China
Company
develops computing technologies and AI server platforms.
What you will do
- Validate topologies and analyze performance across CPU hosts, GPUs, memory, storage, and network components.
- Develop validation plans, execute benchmarks, collect data, and analyze results for CPU host and GPU I/O studies.
- Investigate performance issues with senior engineers and propose improvements from the host platform perspective.
- Collaborate with cross-functional teams to communicate test progress, document technical findings, and support issue closure.
Requirements
- Upcoming graduate with a Master of Science degree or higher in Electrical Engineering, Computer Science, Computer Engineering, or a related technical field.
- Fundamentals in computer architecture, operating systems, or computer systems, including interest in CPU, memory, and I/O behavior.
- Basic knowledge of GPU computing, parallel programming, or accelerator-based systems.
- Interest in AI server and cluster-level architecture, networking, storage, scale-up, and scale-out design.
- Programming and scripting skills in Python, C/C++, or shell scripting for test automation, data processing, and performance analysis.
- Good verbal and written English communication skills are required.
Nice to have
- Exposure to PCIe/CXL, coherency, IOMMU, NUMA, or host-device data movement.
- Experience with CUDA, ROCm, OpenCL, SYCL, or related GPU and AI accelerator frameworks.
- Experience with system validation, performance testing, Linux development, machine learning workloads, networking, storage, or GPU computing through internships, research, coursework, or academic projects.
Culture & Benefits
- Hands-on learning opportunities in modern AI infrastructure and server performance engineering.
- Work with experienced engineers and cross-functional technical teams.
- Exposure to single-server performance tuning and cluster-scale design concepts.
- Full-time college graduate position with on-site work in Shanghai.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →
Похожие вакансии
6 дней назад
Performance Engineer (China Market)
6 дней назад
Field Application Engineer Intern (Software)
4 дня назад
Sr. Staff Field Application Engineering, Optical Module
6 дней назад
Principal Engineer (ASIC)
1 час назад
Principal Design Engineer - Physical Design (DDR PHY IP)
22 часа назад