Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
развернуть
$160к-350к/год
$180к$220кмедиана$250к
По похожим ролям (49) ~ $220к/год
На СНГ рынке: $3.1к/мес ($2.1к - $3.1к)
88
Крутая вакансия
развернуть
Чёткий фокус на системной производительности, работа с новым AI-железом и сильный пакет льгот делают роль привлекательной, хотя поток срочных запросов может часто переключать внимание.
Поток срочных задач
Передовые технологии
Железо для AI
Сильный соцпакет
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Systems Engineer, Experiments & Integration (AI): Running LLM inference experiments across simulators, hardware emulators, and customer workloads with an accent on performance measurement, integration support, and reusable engineering assets. Focus on profiling memory bandwidth and host-device synchronization, analyzing counters and traces, and turning urgent investigations into repeatable models, scripts, and regression tests.
Location: Remote (United States)
Base salary: $160,000–$220,000 for Mid, $220,000–$270,000 for Senior, and $270,000–$350,000 for Principal.
Company
hirify.global builds AI inference accelerators for low-latency, high-throughput large language model inference, including Atlas systems, the Asimov ASIC, and Titan systems.
What you will do
Respond to simulation and hardware-emulation requests from hardware, software, and customer teams.
Run experiments and demos, including bringing new LLMs up on emulators and testing requested configurations.
Measure and explain performance using counters, execution traces, profiling, and end-to-end timing.
Support simulator and emulation integration for other engineering teams.
Turn investigations into reusable calibrated models, repeatable experiments, scripts, and regression tests.
Requirements
4+ years of hands-on systems or performance engineering experience.
Experience running LLM inference workloads end to end and identifying time spent in weight loading, memory bandwidth, and host-device synchronization.
Strong understanding of performance measurement, including counters, execution traces, profiling, and reporting results with their limitations.
Hands-on experience with host-side driver and runtime code and comfort working close to hardware.
Ability to move quickly on loosely specified requests, make assumptions explicit, and produce repeatable results.
Strong Rust skills, or expert-level C/C++ skills with willingness to work in Rust daily, plus proficiency in Python and fluency with Linux, shell scripting, containers, and CI.
Excellent communication skills, including the ability to provide direct answers, explain their basis, and recommend next steps.
Must currently be authorized to work in the United States.
Nice to have
Experience with Cadence Palladium, Synopsys ZeBu, or FPGA boards.
Experience bringing up new workloads on early or unstable hardware.
Culture & Benefits
Remote-first work with a company-provided computer and home-office setup.
Company-paid medical, dental, vision, life, and disability coverage for employees and dependents, with additional voluntary coverage options.
Unlimited paid time off and 13 paid company holidays.
Competitive salary, equity, and a 401(k) with company matching from day one.
New visa sponsorship is not available; H-1B transfers may be facilitated for eligible candidates.
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 →