Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
развернуть
По международному рынку данных пока нет
На СНГ рынке: $5.3к/мес ($3.9к - $6к)
78
Хорошая вакансия
развернуть
Редкая возможность работать с ML на всём пути до кремния в хорошо профинансированном AI-стартапе, но широкий охват от моделей до инфраструктуры и низкоуровневых систем может сделать задачи напряжёнными.
Широкий круг задач
Современные технологии
Перспективная область
Финансирование роста
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior ML Engineer (AI Hardware): Building and deploying machine-learning models, inference engines, and MLOps pipelines across GPU and AI-accelerator infrastructure with an accent on hardware-aware optimization, model performance, and AI-silicon integration. Focus on adapting architectures and runtimes to NPU constraints, optimizing latency, memory, and power, and delivering AI features from training through deployment with hardware, firmware, and QA teams.
Location: Taipei, Taiwan
Company
hirify.global develops AI-enhanced security processors and silicon-rooted security and management chips, including Trusted Control/Compute Units, for AI data center infrastructure.
What you will do
Optimize training and inference performance across GPU and AI-accelerator infrastructure, including MLOps pipelines.
Design, train, evaluate, and productionize machine-learning models spanning deep learning, LLMs, computer vision, and recommendation systems.
Build or optimize inference engines and serving runtimes for real hardware constraints such as latency, memory, and power.
Work in at least one specialty area: NPU hardening, systems-level software, inference engines, test and verification harnesses, or security-focused ML.
Collaborate with RTL and hardware, firmware, and QA teams to deliver AI features from training through deployment and monitoring.
Requirements
3–5+ years of hands-on AI/ML experience and a Bachelor's degree; a Master's degree is preferred.
Hands-on experience with AI/ML infrastructure and performance, including GPU clusters, distributed training, inference-serving optimization, and MLOps pipelines.
Experience designing, training, and evaluating machine-learning models, as well as taking models into production through feature engineering, data pipelines, and deployment.
Experience with AI-chip or hardware-aware ML, such as optimizing inference engines for a specific chip or adapting model architecture and quantization to chip constraints.
Hands-on experience in at least one specialty area: NPU or AI-accelerator production hardening and model mapping; BMC firmware, embedded Linux, RTOS, or other low-level systems software; inference-engine or serving-runtime optimization; automated hardware or RTL/DV test and verification harnesses; or AI-driven cybersecurity and firmware/hardware security.
Culture & Benefits
Full-time employment in a collaborative, diverse, and multifaceted environment.
Work on real-world AI-silicon and security problems with emphasis on persistence, curiosity, continuous learning, and mutual support.
Join a company founded in 2017 with more than 100 employees and recent funding supporting continued growth.
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 →