Staff AI Model Optimization Architect (LLM & Multimodal)

QUALCOMM, Inc.; Austin (TX); On-site; USD 162,000 - 243,000; Full time

Job summary

Qualcomm Technologies, Inc. in Austin, TX, is seeking a Staff Engineer – AI Model Optimization Architect to lead end-to-end model transformation and optimization for LLMs, VLMs, diffusion, and multimodal models on Qualcomm accelerators.

You will collaborate with compiler, performance, and accuracy teams to translate models into accelerator-efficient execution, balancing throughput, latency, memory, and quality across Day0 to production deployment.

Qualifications

• Expert level PyTorch and inference-focused model optimization.
• Experience with torch.compile / TorchDynamo workflows.
• Deep understanding of transformer architectures, attention mechanisms, MoEs, and performance trade-offs.
• Practical experience with KVcache behavior, serving time optimizations, and memory/performance tradeoffs.
• Strong foundation in computer architecture, ML accelerators, and distributed systems.

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) enabling fused operations and performance-critical rewrites.
• Partner with compiler, performance, and accuracy teams to co-design lowering strategies and runtime integration.
• Profile and optimize LLM/VLM/diffusion inference for throughput and latency across batch sizes, sequence lengths, and serving modes.
• Own transformer-specific optimizations including KVcache management, decoding behavior, and long context performance.
• Enable and optimize continuous batching and dynamic scheduling, impact on memory and tail latency.
• Architect and scale distributed inference strategies across multi-core and multi-device systems.

Skills

PyTorch

Python

Model optimization

Inference optimization

Graph capture

Transformer architectures

KVcache

Distributed systems

Education

Bachelor's degree in CS/Engineering or related field

MS in Computer Science, ML, CE or EE

PhD in a relevant field (bonus)

Tools

TorchDynamo

Torch.compile

ONNX

Triton

Job description

Qualcomm Technologies, Inc. in Austin, TX, is seeking a Staff Engineer – AI Model Optimization Architect to lead end-to-end model transformation and optimization for LLMs, VLMs, diffusion, and multimodal models on Qualcomm accelerators.

You will collaborate with compiler, performance, and accuracy teams to translate models into accelerator-efficient execution, balancing throughput, latency, memory, and quality across Day0 to production deployment.