Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
ЗП не указанаразвернуть
На похожих ролях по рынку
$183к$221кмедиана$285к
48 в выборке
На СНГ рынке: $4.3к/мес ($3.8к - $5к)
92
Отличная вакансия
развернуть
Это перспективная роль в deep-tech компании, занимающейся передовыми разработками в области фотонных вычислений для AI-инфраструктуры.
Трендовый домен
Современный стек
Четкие обязанности
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Software Architect (AI): Developing and benchmarking custom kernels for modern AI accelerator hardware and shaping deployment strategies for optical switching technology across training, inference, and agentic workloads with an accent on distributed AI systems, high-performance networking, and novel network devices. Focus on optimizing communication kernels, exploring deployment architectures, and defining how AI workloads run across next-generation infrastructure.
Location: Hybrid in Oxford, United Kingdom; other locations include the Bay Area, San Francisco, and Heidelberg, Germany.
Company
hirify.global is building photonic switching technology and optical infrastructure for high-speed, ultra-low-latency networking in AI datacenters.
What you will do
Develop, test, benchmark, and document custom kernel code for contemporary AI accelerator hardware.
Analyze benchmark results and derive optimization strategies for communication kernels.
Contribute to the definition and implementation of the AI workload deployment ecosystem.
Track techniques for deploying communication kernels across distributed AI accelerator systems.
Design OCS deployment strategies tailored to training, inference, and agentic AI/ML workloads.
Contribute to the design-space exploration of novel networks and network devices.
Requirements
Very good programming skills in one or more higher-level languages, with strong experience in C++ and Python.
Deep understanding of AI accelerator hardware programming models.
Good knowledge of distributed shared memory architecture concepts.
Strong teamwork, helpfulness, curiosity, innovative thinking, and passion for advancing technology.
Good written and verbal communication skills, including the ability to explain complex technical concepts to broad audiences.
Nice to have
Knowledge of AI/ML and/or HPC workloads and their communication patterns.
Knowledge of CUDA and/or NCCL kernels and their operation on hardware.
Familiarity with the internal architecture of ML frameworks such as PyTorch or TensorFlow.
Familiarity with deploying multi-node compute tasks on compute clusters.
Detailed knowledge of high-performance networking hardware and/or software systems; GPU architecture and programming models are particularly advantageous.
Culture & Benefits
Full-time role in the Technology department.
Hybrid workplace arrangement.
Multidisciplinary environment involving physicists, engineers, and machine learning specialists.
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 →