We need a passionate, hard-working and creative individual to help us optimize future GPU software solutions for DL.
What youll be doing:
Influencing future software and hardware for DL acceleration over GPU solution.
Prototyping and productizing software solutions to take advantage of advanced hardware features, analyzing performance and efficiency, improving the current state of the art solutions.
This will be done across most advanced NNs and state of the art GPU HW.
Increase your knowledge of different NNs, software graph compilation techniques and hardware for DL.
What we need to see:
A student for BS/MS/PhD Computer Science or EE.
Python, DL framework (e.g. TensorFlow, PyTorch), C, C++ programming experience.
Hardware architecture familiarity.
Experience working with deep learning frameworks will be an added advantage.
Ability to self-manage, good analytical skills, and communicate well.
Tight-knit teamwork and interpersonal skills.
Action oriented with strong analytical and problem-solving skills.
Ways to stand out from the crowd:
GPU familiarity and CUDA optimization experience.
Higher education researches in the space of hardware architecture for DL.
