As a Hardware Deep Learning Engineer, you will be responsible for, but not limited to:
2) Identify, evaluate, and develop RTL prototypes of key architectural features that improve the PPA of the NPU IP.
4) Collaborate with the Workload and Algorithm teams to analyze next generation requirements and opportunities, influence and guide research and academic collaboration in the space of Artificial and Deep Learning.
In addition to the qualifications listed below the ideal candidate will also have:
1) Problem-solving skills.
2) Excellent verbal and written communication skills.
4) Self-motivated and proactive with independent thinking mindset as an architect.
Minimum Qualifications:
Bachelor's degree in Computer Science, Electrical Engineering, or related field with 10+ years of experience or Master's degree in Computer science, Electrical Engineering with 7+ years of experience or a PhD degree in Computer science, Electrical Engineering with 5+ years of experience. The industry experience must be in Digital Logic Design / RTL Design using System Verilog and/or Verilog.
3+ years of experience in HW Architecture
2+ years of experience working in the AI/DL domain.
Preferred Qualifications:
1) Experience in AI model architectures, layer types, ops, activation functions.
2) Experience with AI framework, AI models, and basic neural computing operations.
3) Experience with various techniques to optimize models for compute/perf (quantization, compression, sparsity, pruning, low precision).
4) Experience in computer architecture concepts such as pipelining, caching, parallel computing with SIMD/VLIW,multi-core/multi-threading,data precision, memory hierarchy.
5) Experience with data precision, floating point vs. fixed point computing trade-offs.
6) Hands-on experience working with Git (PR/MR workflows with GitHub or any Gitlab repos).
7) Any hands-on work experience of working with few of the modern DL topologies (CNNs, Transformers, LLM, SSM, etc).
8) Experience in mapping between Neural Networks architectures and hardware accelerated inference.
Experienced HireShift 1 (United States of America)US, California, Santa ClaraUS, Arizona, Phoenix, US, California, Folsom, US, Oregon, HillsboroWeoffer 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:
Annual Salary Range for jobs which could be performed in the US:
This role will require an on-site presence. * Job posting details (such as work model, location or time type) are subject to change.
משרות נוספות שיכולות לעניין אותך