LLM Serving Engineer (Cloud AI Engineering), Senior / Staff Engineer

$158,400 – $237,600 · Posted 1 day ago

San DiegoLast seen today

Summary

Build and optimize scalable LLM inference platforms at Qualcomm's Cloud AI team, implementing advanced serving techniques like KV-cache management, speculative algorithms, and model optimization. Contribute to production serving frameworks (vLLM, SGLang, Triton, TGI) and work with customers on deployment solutions. Collaborate with compiler, firmware, and platform teams to drive efficient serving through autoscaling, load balancing, and routing. Requires deep understanding of transformer architectures, strong PyTorch and Python skills, computer architecture knowledge, and hands-on experience profiling and optimizing deep learning workloads.

Data Science DevOps / Infrastructure AI Machine Learning Python Attention Mechanisms Autoscaling Computer Architecture Cuda Data Structures Deep Learning Distributed Systems Generative AI Inference Optimization Kernel Optimization Kserve Kv Cache Management LLM D LLM Large Language Models Lmcache Load Balancing ML Accelerators Model Optimization Moe Mooncake Ollama Parallel Programming Profiling PyTorch Sglang Slm Speculative Decoding System Design Tgi Torch Compile Torchdynamo Transformers Triton Inference Server Triton Kernels Vllm Vlm