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
$160к$187кмедиана$255к
48 в выборке
На СНГ рынке: $3.6к/мес ($3к - $4.7к)
88
Крутая вакансия
развернуть
У роли понятная продуктовая цель и чёткая техническая зона ответственности, а работа объединяет AI и проектирование чипов; офисный формат и ограничения по экспортному контролю сужают круг тех, кому она доступна.
Ограничение по допуску
AI на переднем крае
Понятная зона задач
?Работа из офиса
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
AI/ML Software Engineer, EM and Physics Surrogates (AI/ML, RF chip design): Building production machine-learning surrogate models that replace electromagnetic and thermal simulations inside an AI-native RF chip design platform with an accent on geometric modeling, inverse design, and reliable inference. Focus on automating simulation-based dataset generation, quantifying uncertainty, integrating fallback simulations, and deploying models for manufacturable chip layouts.
Location: Atlanta, Georgia, United States; onsite
Company
hirify.global is building GaNdalph.ai, an AI-native RF chip design platform that uses machine learning to shorten chip design cycles.
What you will do
Build, train, and ship surrogate models predicting electromagnetic responses of inductors, transformers, baluns, matching networks, and other on-chip structures from layout geometry.
Automate large-scale EM simulation campaigns across foundry metal stacks to generate training datasets.
Develop inverse-design optimization and generative methods that produce manufacturable layouts from target responses.
Extend surrogate modeling to thermal behavior in high-power-density designs.
Quantify model error and uncertainty, implement trusted-range fallbacks to full simulation, and integrate models into the GaNdalph.ai design flow for fast inference.
Collaborate with EM design and layout engineers to translate design rules and physical constraints into deployable software.
Requirements
Bachelor’s or Master’s degree in Computer Science, Computer Engineering, Electrical Engineering, Physics, or a related field.
3+ years of professional experience in machine learning or software engineering.
Experience shipping machine-learning models into production, not only training them.
Proficiency in Python, including object-oriented programming, automation, and testing.
Experience building models with PyTorch, TensorFlow, or JAX.
Experience with spatial or geometric data models, such as convolutional networks, graph neural networks, or neural operators.
Solid understanding of algorithms, data structures, numerical methods, and Git version control.
To comply with U.S. Government export regulations, including ITAR, applicants must be U.S. citizens, lawful permanent residents of the U.S., protected individuals, or eligible to obtain the required U.S. Department of State authorizations.
Nice to have
PhD in Electrical Engineering, Computer Science, Computer Engineering, or a related field, with an emphasis on RF/microwave integrated circuit design.
Experience with physics-informed machine learning or surrogate modeling for simulation.
Experience with EM simulation tools such as Ansys HFSS, Cadence EMX, Keysight Momentum, or openEMS.
Knowledge of chip layout formats and tools including GDSII, gdsfactory, or KLayout.
Experience with Bayesian optimization, active learning, or generative design models.
Familiarity with automating simulations through SKILL, AEL, or Python APIs.
Understanding of RF concepts including S-parameters, impedance matching, and quality factor.
Culture & Benefits
Full-time product role focused on shipping measurable, production-ready models.
Competitive salary and equity package.
Comprehensive health, dental, and vision insurance.
401(k) retirement plan.
Paid time off and sick leave.
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 →