Sr. Cloud AI Infrastructure Engineer
Core
Researching AI accelerator hardware logic and optimizing high-performance operator libraries for large-scale cloud computing environments to support LLM inference and training.
Role type
Senior IC cloud AI infrastructure engineer (hardware/architecture)
Builds
High-performance operator libraries, interconnect architectures, and optimized cloud computing environments for LLM workloads.
Domain
Cloud infrastructure, AI hardware, semiconductor architecture, distributed systems
Deliverable
production ML models | infrastructure
Required skills
GPGPU architecture expertise, parallel computing frameworks, low-level operator development (CUDA, Triton), large-scale distributed systems, cluster topology design, high-performance network protocols
Preferred skills
Ultra-large-scale accelerator cluster design, deep learning framework optimization (PyTorch, TensorFlow), semiconductor industry insight
Technologies
CUDA, Triton, PyTorch, TensorFlow, Fat-tree, Torus
Responsibilities
Conduct architecture research on AI accelerator hardware logic and power-efficiency; design and optimize operator libraries for cloud environments; define interconnect architecture for heterogeneous resource pooling; monitor global semiconductor trends and validate emerging technologies.
Seniority
Senior, hands-on IC
