Senior ML Compiler Architect: PyTorch to CUDA & MLIR

MemWize, Inc; Sunnyvale, Northern (CA, KY); Hybrid; USD 180,000 - 240,000; Full time

Job summary

Memwize is a VC-backed stealth-mode startup building rack-level AI inference systems in Sunnyvale, CA. We are seeking a Senior/Principal Machine Learning Compiler Developer to design and implement compiler capabilities from PyTorch through Triton down to CUDA and machine IR on leading-edge accelerators.

Join a fast-moving team focused on performance, scalability, and low-latency inference for next-generation AI workloads.

Qualifications

• We cannot infer explicit qualifications from the HTML.

Responsibilities

• Build compiler capabilities from PyTorch through Triton down to CUDA and machine IR on leading-edge accelerators.

Job description

Memwize is a VC-backed stealth-mode startup building rack-level AI inference systems in Sunnyvale, CA. We are seeking a Senior/Principal Machine Learning Compiler Developer to design and implement compiler capabilities from PyTorch through Triton down to CUDA and machine IR on leading-edge accelerators.

Join a fast-moving team focused on performance, scalability, and low-latency inference for next-generation AI workloads.