Senior/Staff Software Engineer role focused on developing and optimizing LLM inference systems for Qualcomm AI accelerators. Responsibilities include enhancing open-source LLM serving frameworks (llm-d and others), integrating Qualcomm accelerators into inference engines, designing distributed LLM inference capabilities (prefill/decode disaggregation, KV-cache management, model parallelism), and deploying inference workloads on Kubernetes and cloud-native infrastructure.… The role requires strong software engineering skills in Python, C++, Go, or Rust, with deep expertise in machine learning inference systems, distributed systems, AI accelerator software, or cloud-native infrastructure.
San DiegoLast seen today