Principal Deep ISP AI/ML Engineer: Sensors (Computer Vision)
Контакты
Формат работы
hybrid
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
Israel
machine learningcomputer visiondeep learningquantizationlidaredge airadarsensor fusionimage signal processingcomputational imaging
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: $4.7к/мес ($3.8к - $6к)
88
Крутая вакансия
развернуть
Чётко описанная стартовая роль в edge AI сочетает глубокую техническую ответственность с возможностью собрать новую команду, но широта задач и высокий уровень делают её непростой.
?Много ответственности
Современный AI
Создание команды
AI на чипах
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Principal Deep ISP AI/ML Engineer: Sensors (Computer Vision): Building learned camera ISP, low-light enhancement, and multimodal sensing pipelines that run on analog edge compute with an accent on computational imaging, hardware-aware training, and sensor data quality. Focus on designing models for constrained hardware, building datasets and objective/perceptual/task-level evaluation, and extending the system to radar, lidar, and multi-sensor fusion.
Location: Israel; hybrid workplace. Travel up to 10% of the time.
Company
hirify.global builds analog compute silicon for running deep learning at edge power budgets.
What you will do
Own the learned pipeline, including architecture, training, and evaluation for a model replacing hand-tuned signal-processing chains, beginning with camera ISP and low-light enhancement.
Design networks for hirify.global’s analog compute using quantization-aware and hardware-aware training, memory and bandwidth budgets, and hardware mapping with the AI engineering team.
Extend learned sensing to radar, lidar, other modalities, and multi-sensor fusion.
Build the quality-science lab, defining objective, perceptual, and task-level metrics and benchmarking against best-in-class pipelines.
Build capture rigs, proprietary datasets, sensor-noise simulation, and tooling for per-sensor and per-application retraining and auto-tuning.
Deliver customer-data demos and initial design-ins, while hiring and mentoring engineers, publishing, and creating patents.
Requirements
10+ years of experience in computer vision, imaging, or sensor signal processing with deep learning, with continued hands-on work.
MSc or PhD in EE, CS, or a related field.
Knowledge of computational imaging, including RAW-domain processing, noise, denoising, HDR, or color.
Experience taking models from research to a shipped product and owning data, training, and evaluation.
Experience with constrained hardware, including quantization, edge NPUs, and compute and memory budgets.
Ability to travel up to 10% of the time.
Nice to have
Experience with radar, lidar, depth, thermal sensing, or multi-sensor fusion.
Publications at CVPR, ICCV, or ECCV, or granted patents.
Experience with non-standard or in-memory accelerators, sensor-level work, leading a small team, or building a product from zero.
Culture & Benefits
Collaborative and respectful environment with tools and support for delivering high-quality work.
Professionalism, creativity, integrity, and inclusion are valued.
Equal employment opportunity is provided without discrimination or harassment based on protected characteristics.
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 →