Performance & Modeling Engineer
Core
Deploy, enable, benchmark, and optimize state-of-the-art AI models (LLM, MoE, multimodal) on Qualcomm Cloud AI platforms to deliver best-in-class inference efficiency for cloud-scale AI deployments.
Role type
Senior IC Performance & Modeling Engineer (Cloud AI)
Builds
Cloud-scale AI inference systems and optimized AI workloads
Domain
Cloud AI / Large Language Models / AI Infrastructure
Deliverable
production ML models
Required skills
Python, C++, Linux, Transformer architectures, LLMs, MoE models, graph optimization, model compilation, AI frameworks (PyTorch, ONNX, TensorFlow, JAX), AI serving frameworks (vLLM, SGLang, TGI, TensorRT-LLM, LMDeploy)
Preferred skills
AI accelerator platforms, Quantization, KV-Cache optimization, speculative decoding, continuous batching, Prefix Caching, Parallelism Strategies, distributed inference, Roofline analysis, Kubernetes, Docker, cloud-native AI infrastructure
Responsibilities
Deploy and optimize LLM, MoE, and multimodal models; Analyze and improve model accuracy, latency, throughput, memory utilization, and scalability; Drive graph-level, framework-level, and system-level optimizations; Benchmark AI workloads and identify performance bottlenecks; Work with compiler, runtime, kernel, and architecture teams; Support customer deployment and production readiness
