Пост объединяет несколько разных вакансий в одном заголовке, так что это просто список ролей, а не конкретное предложение.
Смесь ролей
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Staff ML Accelerator Architect Software Engineer (GPU/ML Accelerators): Architecting and optimizing high-performance machine learning compute solutions for autonomous driving with an accent on workload mapping, custom hardware, model optimization, and performance evaluation. Focus on designing hardware-friendly implementations, building scalable simulator tools, and balancing hardware, compiler, and model architecture trade-offs.
Location: On-site in Mountain View, California, or New York City, New York
Salary: $170,000–$216,000 USD base salary per year
Company
Waymo develops autonomous driving technology and the Waymo Driver for fully autonomous ride-hail services and other vehicle platforms.
What you will do
Analyze workloads and map them efficiently to CPUs, GPUs, and machine learning accelerators.
Architect, simulate, and design machine learning solutions for autonomous driving.
Propose hardware-friendly implementations and project performance, power, and latency.
Collaborate with compiler and model developers on engineering trade-offs and future model architectures.
Build scalable tools for simulator modeling and performance evaluation.
Work with cross-functional engineering teams to identify requirements and optimization opportunities.
Requirements
Bachelor’s degree in Computer Science, Computer Engineering, or a related technical field, or equivalent practical experience.
At least 3 years of experience designing or architecting complex, high-performance CPU, GPU, or machine learning accelerator architectures, including through doctoral research.
At least 1 year of experience with machine learning architectures, acceleration, and model optimization.
Strong C++ programming and algorithmic problem-solving skills.
Ability to work on site in Mountain View or New York City.
Nice to have
Experience modeling high-performance architectures in cycle-aware simulators.
Experience analyzing workloads and delivering novel hardware-software solutions that improve performance and efficiency.
Familiarity with machine learning model architectures, compute bottlenecks, and optimization opportunities.
Experience with microarchitecture design using SystemVerilog or HLS.
Culture & Benefits
Work in a multidisciplinary Compute Team developing a high-performance automotive compute platform.
Collaborate closely across hardware, software, compiler, and machine learning engineering functions.
Eligibility for a discretionary annual bonus program and equity incentive plan.
Company benefits are available subject to eligibility requirements.