Founding Engineer (Systems + ML)
职位介绍
Lead end-to-end ML-enabled chip design optimization pipelines, from high-performance kernels to efficient IO and latency-sensitive inference.
Explore novel ML architectures that deliver 1000x performance gains over existing methods.
Build scalable systems capable of handling terabytes of data in seconds and deploy to customers while fixing prod issues on the fly.
Expert in PyTorch, CUDA, memory and latency tradeoffs, and GPU profiling; design, train, and deploy custom models (not GPT wrappers).
Toggle between model architecture design, low-level optimization, and scalable system design for projects with N > 10M.
Thrive in a fast-paced, customer-facing environment with ownership mindset and rapid learning.
Explore novel ML architectures that deliver 1000x performance gains over existing methods.
Build scalable systems capable of handling terabytes of data in seconds and deploy to customers while fixing prod issues on the fly.
Expert in PyTorch, CUDA, memory and latency tradeoffs, and GPU profiling; design, train, and deploy custom models (not GPT wrappers).
Toggle between model architecture design, low-level optimization, and scalable system design for projects with N > 10M.
Thrive in a fast-paced, customer-facing environment with ownership mindset and rapid learning.
查看完整职位
工作职责、任职要求、技能与福利 — 免费创建账号即可查看。
或
已有账户？
登录相似职位
其他可能适合您的职位。