Qualcomm Technologies is hiring a Staff Engineer – AI Model Optimization Architect to join its Cloud AI team, focusing on developing hardware and software platforms for efficient inference of large-scale foundation models. This senior role involves architecting model optimization strategies that transform PyTorch models into accelerator-efficient execution, working closely with compiler, performance, and accuracy teams to ensure optimal throughput, latency, memory usage, and quality across various batch sizes and sequence lengths. Key responsibilities include designing fusion kernels using DSL-based approaches like Triton, profiling and optimizing large language and vision models for inference, enabling continuous batching strategies, and scaling distributed inference across multi-core systems. The ideal candidate has expert-level proficiency in PyTorch, experience with torch.compile, deep knowledge of transformer architectures, and a strong foundation in computer architecture and ML accelerators.
Architect and deliver model optimization strategies for PyTorch models on Qualcomm accelerators.
Drive graph capture and deployment using PyTorch, ONNX, and torch.compile for efficient execution.
Design and implement fusion kernels to enable performance-critical algorithmic rewrites.
Profile and optimize LLM/VLM/diffusion inference for throughput and latency across various conditions.
Own transformer-specific optimizations including KVcache management and long context performance.
Enable and optimize continuous batching for memory, scheduling, and tail latency improvements.
Architect distributed inference strategies to scale model optimizations across multi-core systems.
What we're looking for
Expert level expertise in PyTorch and model optimization for inference.
Hands-on experience with torch.compile/TorchDynamo or similar graph capture workflows.
Deep understanding of transformer architectures, attention mechanisms, and performance trade-offs.
Practical experience with KVcache behavior and memory/performance optimizations.
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, or related field.
Market check
Salary context
Competitive pay
How this pay compares to similar roles
Similar $204k
This role $198k
$147k
most similar roles pay here
$261k
This role pays less than
57%
of similar roles. Most pay
$162,000–$246,150
— the shaded band above.
At the midpoint, this role pays about
$198k
versus about
$204k
for comparable roles.
Based on 240 similar postings.
Employer
About Qualcomm
Qualcomm is a leading American semiconductor and telecommunications company based in San Diego, CA.
Qualcomm currently has
595 open roles
on FindRole.
Listed pay typically runs
$148,300–$222,500
across 540 roles with salary data.