6 дней назад
Software Engineer, GPU Performance (AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Software Engineer, GPU Performance (AI): Optimizing model execution and inference infrastructure for AI video applications with an accent on GPU profiling, latency, throughput, and cost efficiency. Focus on developing high-performance GPU kernels, improving batching and memory management, and building benchmarks that prevent performance regressions across video workloads.
Location: Los Angeles, Palo Alto, San Francisco, Toronto, or Singapore
Company
A visual storytelling technology company building AI applications for avatar creation, interactive video, and video translation.
What you will do
- Profile GPU utilization, kernel execution, memory bandwidth, and CPU–GPU data movement using NVIDIA Nsight Systems, Nsight Compute, and PyTorch Profiler.
- Identify and measure bottlenecks across model execution, preprocessing, and inference serving.
- Improve latency, throughput, GPU utilization, and cost through batching, scheduling, and memory management.
- Develop or integrate high-performance GPU kernels when existing implementations limit performance.
- Build benchmarks and automated regression checks for representative video workloads.
- Collaborate with AI researchers and infrastructure engineers to bring optimizations into production.
Requirements
- Experience optimizing GPU-based AI workloads or high-performance computing systems.
- Strong Python skills and experience with PyTorch or a similar machine learning framework.
- Understanding of GPU hardware concepts including memory bandwidth, cache behavior, tensor cores, and CPU–GPU data movement.
- Experience using profiling tools to connect hardware behavior with application bottlenecks and validate improvements.
- Ability to turn performance experiments into reliable production changes and communicate tradeoffs clearly.
Nice to have
- Experience with CUDA, Triton, or C++ GPU programming.
- Experience optimizing video, image, audio, diffusion, or Transformer models.
- Familiarity with multi-GPU inference, GPU interconnects, quantization, or large-scale model serving.
- Experience building performance benchmarks or regression testing infrastructure.
- Prior experience in a fast-paced technology environment.
Culture & Benefits
- Competitive salary and benefits package.
- Dynamic and inclusive work environment.
- Opportunities for professional growth and advancement.
- Collaborative culture focused on innovation and creativity.
- Access to current technologies and tools.
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
Engineer (AI/ML Systems)
Anthropic
8 дней назад
Performance Engineer (AI)
280 000 - 850 000$
Baseten
8 дней назад
Software Engineer (AI)
180 000 - 360 000$
11 дней назад
Inference Performance Engineer (AI)
6 дней назад
Machine Learning Systems Engineer (AI)
7 дней назад
HPC and AI Performance Engineer (HPC/AI)
105 500 - 243 000$