below marketmost similar roles pay hereabove market
This role pays less than
84%
of similar roles. Most pay
$173,968–$235,750
— the blue band above.
At the midpoint, this role pays about
$158k
versus about
$205k
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
580 open roles
on FindRole.
Listed pay typically runs
$147,900–$218,400
across 557 roles with salary data.
The Senior AI Performance Architect joins the Machine Learning Engineering team to drive functional, performance, and power enhancements into hardware for state-of-the-art AI training. This role involves architecting flexible computational blocks supporting various datatypes and precisions, designing memory subsystems for capacity and bandwidth, and developing scale-out architectures including switches and NoCs. You will perform competitive analysis, define performance models, and conduct pre-silicon predictions for ML training workloads. Key requirements include expertise in GPU architectures, LLM hardware requirements, and experience with distributed training frameworks like DeepSpeed or FSDP. The role utilizes C++, Python, and front-end frameworks like PyTorch or TensorFlow. You will solve technical challenges in scaling AI inference and training systems across large numbers of accelerators, servers, and racks for diverse end devices.
AI Systems
Computer Architecture
Performance Modeling
High-Performance Computing
Distributed Systems
Python
C++
CUDA
Triton
ROCm
HIP
Data Parallelism
HBM
PCIe
Compilers
CUDA
C++
Python
GPU Architecture
Deep Learning
Neural Networks
Performance Modeling
MLPerf Training
Computer Architecture
System Simulators
Performance Analysis
Drivers
DL Frameworks
x86 System Architecture
machine-learning
ETW
WPA Trace Analysis
OS Scheduling
Control Frameworks
Benchmarking
Hardware
Firmware
Operating Systems
AI Tools