Qualcomm
Principal SW Engineer - LLM Serving (Cloud AI)
$224K–$335K
San Diego, California · On-site · Principal · Full-time · Posted Sep 17, 2026
- Experience
- Bachelor's degree: 8+ years; master's degree: 7+ years; PhD: 6+ years in hardware, software, systems engineering, or related work.
- Education
- Bachelor's, master's, or PhD in Computer Science, Engineering, Information Systems, or a related field.
About the job
Develop and deploy software for accelerating cloud AI inference, with a focus on serving large language models and optimizing performance across multicore and SoC architectures.
What you'll do
- Plan, manage, and deliver commercial software projects across the product lifecycle, from R&D to deployment.
- Develop and optimize LLM serving software and neural networks, analyzing performance bottlenecks on multicore systems.
- Work cross-functionally on systems, software, integration, and testing.
What they ask for
- Experience with serving frameworks such as vLLM and strong development skills in PyTorch.
- Strong understanding of LLMs, multimodal and reasoning models, and neural-network execution and optimization.
- Experience writing high-performance multicore software; skills in C++ and Python and performance analysis of software/hardware on multicore architectures.
- Understanding of multicore and SoC architectures, including performance modeling.
Nice to have
- Experience with machine learning accelerators and related software.
- Background in neural-network operators, linear algebra, and math libraries.
Pay
$223,600.00 - $335,400.00 USD base salary
Tools
vLLM, PyTorch, C++, Python, PCIe, NoCs
AI focus
Develop and optimize cloud AI inference acceleration and LLM serving; work with LLMs, multimodal and reasoning models, neural networks, and machine learning accelerators.
Model-written summary · the original posting is authoritative