This role pays less than
79%
of similar roles. Most pay
$159,750–$248,853
— the shaded band above.
At the midpoint, this role pays about
$154k
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
639 open roles
on FindRole.
Listed pay typically runs
$146,400–$221,900
across 619 roles with salary data.
The LLM Serving Engineer joins the Machine Learning Engineering team to create and implement machine learning techniques, frameworks, and tools for various technology verticals. This role involves modeling, architecting, and developing machine learning hardware co-designed with software for inference or training solutions. The engineer will develop optimized software such as machine learning kernels, compiler tools, and model efficiency tools to enable AI models on specific hardware features. Day-to-day responsibilities include prototyping complex algorithms, conducting experiments to train and evaluate models, and extending runtime frameworks with new optimizations. Required skills include proficiency in Python, R, C, or C++, experience with frameworks like TensorFlow, Keras, or PyTorch, and knowledge of statistics and probability. The role focuses on solving technical challenges in mobile, edge, auto, and IOT products through hardware and software integration.
Computer Vision
Deep Learning
Python
C++
PyTorch
TensorFlow
Keras
Caffe
Linux
Android
QNX
Quantization
Pruning
Distillation
CPU
GPU
DSP
NPU
Containerization
Machine Learning
C++
Python
Matlab
TensorFlow
PyTorch
Keras
Signal Processing
Communication Theory
Neural Networks
Convex Optimization
Numerical Analysis
Information Theory
Channel Coding
Systems Engineering
LLM
PyTorch
Python
Triton-Inference Server
vLLM
SGLang
CUDA
Triton
torch.compile
torchDynamo
Distributed Systems
Kernel Design
Deep Learning
KV-Cache Management
Model Optimization