Senior/Staff AI Model Optimization Architect – Hsinchu/Taipei

About the role

Qualcomm's Cloud AI team is looking for a Staff‑level AI Model Optimization Architect to lead end‑to‑end transformation and optimization of large language, vision, diffusion and multimodal models on Qualcomm inference accelerators. The role works closely with compiler, performance and accuracy teams to deliver efficient inference across a range of workloads.

Key responsibilities

• Architect and deliver model optimization strategies that transform PyTorch models for efficient inference on Qualcomm accelerators.
• Drive graph capture and deployment using PyTorch, ONNX, and torch.compile, including model rewrites and graph‑level transformations.
• Design and implement fusion kernels using DSL‑based approaches (e.g., Triton) to enable fused operations and performance‑critical algorithmic rewrites.
• Partner with compiler, performance and accuracy teams to co‑design lowering strategies, kernel fusion, layout decisions and runtime integration.
• Profile and optimize LLM/VLM/diffusion inference for throughput and latency across batch sizes, sequence lengths and serving modes.

Required profile

• Expert level expertise in PyTorch and inference‑focused model optimization with strong Python engineering skills.
• Deep understanding of transformer architectures, attention mechanisms, MoEs and performance trade‑offs.
• Strong foundation in computer architecture, ML accelerators and distributed systems.
• Proven ability to lead cross‑functional technical efforts and influence design decisions.
• MS in Computer Science, Machine Learning, Computer Engineering, Electrical Engineering or equivalent; or higher degree with relevant experience.

Required skills

• PyTorch, torch.compile, TorchDynamo.
• ONNX and graph capture workflows.
• Python programming.
• DSL‑based kernel development (e.g., Triton).
• Transformer model optimization, KV‑cache management, continuous batching.