42 минуты назад
Inference Performance Engineer (AI)
Вакансия из Hirify Global, списка международных tech-компанийДля мэтча и отклика нужен Plus
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Inference Performance Engineer (AI): Build and optimize performance models, kernel micro code, and system-level tools to enhance ML model inference speed and throughput on the Cerebras WSE. Focus on debugging, performance profiling, and developing infrastructure for performance visualization and diagnostics.
Location
Location: US and Canada Offices
Company
Systems builds the world's largest AI chip, delivering industry-leading training and inference speeds that transform AI application experiences.
What you will do
- Build performance models to estimate ML model inference performance.
- Optimize and debug kernel micro code and compiler algorithms for improved inference speed and compute utilization.
- Analyze and debug runtime performance on system and cluster levels.
- Develop tools and infrastructure for visualizing performance data from the Wafer Scale Engine and compute cluster.
Requirements
- Bachelor's, Master's, or PhD in Electrical Engineering or Computer Science
- Strong background in computer architecture
- Experience with low-level deep learning/LLM math
- 3+ years in relevant domains such as Computer Architecture, CPU/GPU Performance, Kernel Optimization, HPC
- Experience with CPU/GPU simulators and performance profiling/debugging
- Proficiency in C++ and Python
Culture & Benefits
- Work on breakthrough AI platform beyond GPU constraints.
- Opportunity to publish and open source cutting-edge AI research.
- Engage with one of the fastest AI supercomputers globally.
- Enjoy job stability combined with startup vitality.
- Simple, non-corporate work culture respecting individual beliefs.
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 →