Skip to main content
搜索所有职位

Sparsity Attention/KVCache Compression algorithm Intern

上海, 上海, 中国 职位 ID JR0274184 职位类别 Intern/Student 工作模式 On-site Required 经验级别 Intern 工时类型 全职
申请

Job Description


Attention and KVCache are the core LLM component. Reduce computation and storage in attention and KVCache will boost inference performance on HW platform. It is critical to explore the various algorithm alternatives to build our technical strength on Xeon as HN and AI appliance solution. We are looking for passionate Intern talent to research and develop sparsity attention and KV Cache compression algorithms for LLM in Intel Platform.

Qualifications


� Master's or Ph.D. student in Computer Science, Artificial Intelligence, Software Engineering, or related fields � Strong background in deep learning, LLMs, or NLP � Familiarity with model compression techniques (e.g., quantization, pruning) � Proficiency in Python or other programming languages � Passion for technology and innovation, with a strong drive to explore and push boundaries � Experience with LLMs (e.g., Mistral, LLaMA, Qwen) is a plus � Knowledge of hardware acceleration (e.g., GPU, TPU, or custom AI accelerators) is a good plus � At least 3 days per week, able to commit to a one-year internship Location: Shanghai

Inside this Business Group


The Data Center & Artificial Intelligence Group (DCAI) is at the heart of Intel’s transformation from a PC company to a company that runs the cloud and billions of smart, connected computing devices. The data center is the underpinning for every data-driven service, from artificial intelligence to 5G to high-performance computing, and DCG delivers the products and technologies—spanning software, processors, storage, I/O, and networking solutions—that fuel cloud, communications, enterprise, and government data centers around the world.


Posting Statement


All qualified applicants will receive consideration for employment without regard to race, color, religion, religious creed, sex, national origin, ancestry, age, physical or mental disability, medical condition, genetic information, military and veteran status, marital status, pregnancy, gender, gender expression, gender identity, sexual orientation, or any other characteristic protected by local law, regulation, or ordinance.

Benefits


We offer a total compensation package that ranks among the best in the industry. It consists of competitive pay, stock, bonuses, as well as, benefit programs which include health, retirement, and vacation. Find more information about all of our Amazing Benefits here.


Working Model


This role will require an on-site presence.* Job posting details (such as work model, location or time type) are subject to change.
申请
Maggie, Offensive Security Researcher

Maggie 前沿安全研究员

“我一直梦想改变世界。在英特尔,我能发挥所长,并且更有自信。因此,我放眼完成壮举。”

  • DevOps infra - k8s Engineer 多个地点 立即申请
  • Infrastructure Devops Platform Engineer 聖荷西, 哥斯达黎加 立即申请
  • System Power and Performance Engineer 希尔斯伯勒, 俄勒冈州 立即申请
查看我们提供的所有机会

您还没有最近查看的职位。

浏览所有工作

您还没有保存的工作。

浏览所有工作