below marketmost similar roles pay hereabove market
This role pays less than
55%
of similar roles. Most pay
$166,837–$249,000
— the blue band above.
At the midpoint, this role pays about
$202k
versus about
$208k
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
575 open roles
on FindRole.
Listed pay typically runs
$147,900–$221,900
across 550 roles with salary data.
The LLM Serving Engineer (Cloud AI Engineering), Senior / Staff Engineer joins the Machine Learning Engineering team to develop hardware and software solutions for inference acceleration. This role involves building a scalable LLM inference platform using techniques like disaggregated serving, KV-Cache management, and specialized kernels. You will contribute to serving packages such as vLLM, SGLang, and Triton-Inference server while collaborating with internal compiler and firmware teams to drive efficient serving through smart autoscaling and load balancing. The position requires proficiency in Python, PyTorch, and distributed systems, alongside a deep understanding of transformer-based architectures, MoEs, and attention mechanisms. You will analyze and optimize deep learning workloads, utilizing your knowledge of computer architecture and ML accelerators to solve complex inference optimization problems within the Cloud AI domain.
Build a scalable LLM inference platform using techniques like disaggregated serving and KV-Cache management.
Contribute to the development of LLM serving packages such as vLLM, SGLang, and Triton-Inference server.
Identify new optimization opportunities by analyzing advanced algorithms like attention mechanisms and MoEs.
Drive efficient serving through smart autoscaling, load balancing, and routing.
Engage with open-source serving communities to evolve and improve the framework.
Analyze, profile, and optimize deep learning workloads for high-performance inference.
Collaborate with internal compiler, firmware, and platform teams to drive customer solutions.
What we're looking for
Bachelor's degree in a related field and 4+ years of engineering experience, OR Master's degree and 3+ years, OR PhD and 2+ years.
Hands-on experience with LLM serving or orchestration packages like Triton-Inference Server, vLLM, SGLang, Ollama, llm-d, KServe, LMCache, or MoonCake.
Deep understanding of foundational LLMs, VLMs, SLMs, and transformer-based architectures.
Strong experience developing language models using PyTorch.
Strong computer science fundamentals in algorithms, data structures, parallel and distributed programming, and computer architecture.
Strong Python development skills for large-scale projects.
Experience analyzing, profiling, and optimizing deep learning workloads.
Open-source contribution to any GenAI package (preferred); PhD in Computer Science, Computer Engineering, or Machine Learning (preferred).