- Irvine, California, United States
- $275K–$275K per year
- 10+ years
Lead the design and optimization of AI inference systems, integrating advanced memory and compute technologies to deliver high-performance, scalable solutions.
Compensation
Salary Range: $275,000
Responsibilities
- Develop deep understanding of modern AI inference workloads and system-level behavior
- Analyze execution characteristics of LLMs, generative AI, and multimodal inference
- Identify bottlenecks in compute, memory, interconnect, and software
- Architect software infrastructure for heterogeneous memory and compute resources
- Evaluate and contribute to AI software stacks such as PyTorch, CUDA, ROCm, Triton, vLLM
Requirements
- Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or a related technical field; PhD is a plus
- Nice to have: LLM inference
- Nice to have: Transformer architecture
- Nice to have: KV cache
- Nice to have: vLLM