10 дней назад
AI Software Solutions Engineer
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
AI Software Solutions Engineer (AI/Intel Hardware): Researching, developing, and optimizing end-to-end AI software stacks, model pipelines, and runtime accelerators for Intel client and edge platforms with an accent on AI frameworks, neural network architectures, hardware acceleration, and model performance. Focus on implementing inference pipelines, optimizing quantization and model parameters, building production-grade software, and benchmarking workloads across CPUs, GPUs, and NPUs.
Location: Taipei, Taiwan; on-site presence required
Company
Intel Corporation's advanced client AI technology group develops optimized AI solutions for Intel hardware and supports customer adoption of AI products.
What you will do
- Research and prototype AI solutions for Intel products and diverse customer applications.
- Design, implement, and optimize end-to-end AI software stacks, model pipelines, and runtime accelerators for CPUs, GPUs, and NPUs.
- Develop open-source libraries, models, tools, and production-grade AI software.
- Optimize models, parameters, code, and quantization using AI frameworks, algorithms, and hardware expertise.
- Collaborate with algorithm, framework, product development, and customer teams to enable applications and future hardware.
- Develop benchmark collateral and identify workloads that inform product requirements and drive innovation.
Requirements
- Bachelor's degree in Computer Science, Data Science, Software Engineering, or a related field; a Master's degree is also accepted.
- Proficiency in Python, C++, or similar programming languages.
- Familiarity with AI frameworks such as TensorFlow and PyTorch, including optimization techniques.
- Practical experience with PyTorch and/or ONNX, including custom modules, forward passes, or inference pipelines.
- Understanding of modern neural network architectures, including Transformers, Attention mechanisms, CNNs, Diffusion models, and MoE.
- Ability to work on-site in Taipei, Taiwan.
Nice to have
- Experience with open-source inference frameworks such as llama.cpp, vLLM, TensorRT-LLM, or Hugging Face TGI.
- Familiarity with AI agent frameworks or multimodal pipelines such as LangChain, AutoGen, CrewAI, Whisper ASR, FastSpeech/VITS, Stable Diffusion, or YOLO.
- Strong communication skills and the ability to collaborate across technical teams.
- Ability to learn and adapt quickly in dynamic environments.
Culture & Benefits
- Collaborative environment involving internal engineering teams, customers, partners, and senior architects.
- Opportunity to contribute to advanced client AI technologies and high-performance computing.
- Focus on bringing research prototypes into production-grade software.
- Ethical hiring practices with no recruitment, medical examination, or other hiring fees.
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 →