Data Center LLM Optimization Customer Engineer
Core
Deploy and optimize LLM inference workloads on Qualcomm Cloud AI accelerator platforms for strategic customers and partners.
Role type
Senior IC ML/Systems Engineer (LLM inference optimization)
Builds
Efficient LLM inference configurations on accelerator, memory, and cluster hardware
Domain
Data Center AI / High-Performance Computing
Deliverable
production ML models
Required skills
LLM inference optimization, distributed AI, Linux systems, Python scripting, performance profiling, model quantization, debugging
Preferred skills
vLLM, TensorRT-LLM, SGLang, DeepSpeed, RDMA/RoCE/InfiniBand, MoE architectures, MLPerf Inference methodology
Technologies
PyTorch, Docker, Kubernetes, C++, Bash, RDMA, InfiniBand, Ethernet
Responsibilities
Profile and optimize prefill/decode performance (TTFT, TPOT, throughput); analyze runtime bottlenecks across compute/memory/network; tune distributed inference parallelism; execute benchmarking and stress tests; debug cross-layer performance issues; build automation tooling; support customer PoCs and production deployments.
Seniority
Senior, hands-on IC
