AI Research Engineer (OpenVINO)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
AI Research Engineer (OpenVINO): Developing state-of-the-art neural network compression algorithms for the NNCF framework with an accent on inference optimization and high-performance computing. Focus on researching and implementing quantization, pruning, and sparsity techniques to enhance model efficiency within the OpenVINO ecosystem.
Location: Must be based in or able to work on-site in Leixlip, Ireland (Hybrid model).
Salary: €76,900–€120,100
Company
A global leader in semiconductor technology, driving innovation in AI, client, and data center software stacks.
What you will do
- Research and develop state-of-the-art neural network compression algorithms.
- Optimize high-performance neural network inference within the OpenVINO ecosystem.
- Collaborate on the Neural Network Compression Framework (NNCF) development.
- Apply deep learning model optimization techniques including quantization, pruning, and sparsity.
- Work with modern deep learning frameworks like PyTorch and TensorFlow.
Requirements
- Master's or PhD in Computer Science, Mathematics, or related field.
- At least 3 years of software development experience.
- Proven experience in deep learning model optimization (quantization, pruning, or sparsity).
- Proficiency in Python and modern programming paradigms.
- Experience with PyTorch, TensorFlow, and OpenVINO.
- English proficiency: Upper-intermediate or advanced (B2+).
Nice to have
- Understanding of hardware-aware optimization for CPU, GPU, and NPU.
- Familiarity with Large Language Model architectures (Transformers, Diffusers).
Culture & Benefits
- Hybrid work model allowing flexibility between on-site and off-site work.
- Competitive total compensation package.
- Opportunity to work on foundational AI technologies and industry-leading software stacks.
- Inclusive work environment with strong commitment to equal opportunity.
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 →