AI Frameworks Engineer
Shanghai, Shanghai Shi, China
ID Pekerjaan JR0260915
Kategori Kerja Software Engineering
Mod Kerja On-site Required
Tahap Pengalaman Experienced
Job Description
Come join a customer-oriented engineering team, whose responsibilities range from: � Conduct Deep learning model and inference pipeline workload debugging and optimization to accelerate AI product landing which based on Intel Architecture and technical solution. � Be proficient in Intel Deep learning framework (Intel OpenVINO) primitives, features, API, toolkits, and use to deliver competitive performance in customer projects. � Implement customized operations, graph fusion, and low-precision/compression optimization programs - mapped on customer requirements. � Debug performance bottlenecks and optimize application with multithreading, vectorization skills. � Deliver efficient technical training and support for internal/external customer projects.Qualifications
� BS/MS in AI/ML, Computer Science, Software Engineering, or a similar field. � At least 3-4 years of excellent experience in C and/or C++ and/or Python in Linux/Windows system programming skills. � Experience in deep learning model inference and fine-tuning optimization: generative AI, common Transformers (Vision/NLP/Speech), CV, Recommendation etc. � Experience with the deep usage of at least 2 Deep Learning frameworks in OpenVINO, TensorRT, PyTorch, HuggingFace/Optimum, ONNXRuntime, TensorFlow etc. � Experience in PTQ/QAT/GPTQ and compression algorithm usage and tuning. � Knowledge of modern processor architecture, for example, Intel architecture (x86), Nvidia/AMD GPU platform. The following will be an additional advantage: � Proficient in OpenVINO/IPEX/ITEX/oneDNN development and/or usage programming. � Experience of kernel operations implementation and optimization for public/private AI frameworks. � Experience in SQ/AWQ/QLoRA tuning. � Experience in low level optimization, vectorization by OpenCL/SYCL/Intel Intrinsics programming and BLAS libraries theory and usage skills. � Experience in performance profiling by Vtune, GPUView, etc. and debugs by GDB, VS etc. � Experience of deployment and performance tuning on public cloud deployment and/or industry edge platform and/or client workstation/PC. � Experience of system profiling (OS kernel/Driver/memory) and HW tuning (PTAT).Inside this Business Group
The Network & Edge Group brings together our network connectivity and edge into a business unit chartered to drive technology end to end product leadership. It's leadership Ethernet, Switch, IPU, Photonics, Network and Edge portfolio is comprised of leadership products critically important to our customers.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.Maggie Offensive Security Researcher
Saya sentiasa mahu melakukan sesuatu yang mengubah dunia — di Intel, saya rasa dihargai, dan saya semakin yakin pada diri saya sendiri. Ia membuatkan saya berasa seperti saya mampu melakukan perkara yang hebat.
- Asia Invoice Center Intern Shanghai, China Mohon sekarang
- AI Software Intern Shanghai, China Mohon sekarang
- Design Verification Engineer - Foundry Services Berbilang Lokasi Mohon sekarang
Anda belum mempunyai Kerja Disimpan lagi.
Lihat Semua PekerjaanSertai komuniti bakat kami
Jadilah orang pertama untuk mendapatkan berita perkembangan terkini di Intel! Daftar untuk menerima berita terkini.