Principal SW Engineer, LLM Serving

Qualcomm

Confirmed live today High trust

Quick summary

Work type
On-site
Location
San Diego, CA
Salary
$223,600–$335,400 / yr
Posted
40 days ago
Freshness
Confirmed live today
Closes
Mar 16, 2027
Nearby
99+ roles within 25 mi

Market check

Salary context

Above market

How this pay compares to similar roles

Similar $212k
This role $280k
$121k $358k
below market most similar roles pay here above market

This role pays more than 84% of similar roles. Most pay $174,600–$250,250 — the blue band above. At the midpoint, this role pays about $280k versus about $212k 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.

Most-posted roles

View all roles at Qualcomm

At a glance

TL;DR · Principal SW Engineer, LLM Serving

Role Posting Log in to save

The Principal SW Engineer - LLM Serving (Cloud AI) joins the Cloud AI team to develop software solutions for Inference Acceleration. This role involves the entire product life cycle, from early R&D to commercial deployment, requiring the delivery of large commercial software projects. The engineer will execute, analyze, and optimize neural networks while writing high-performance software for multicore systems. Key responsibilities include performance modeling of SoC architectures and analyzing software/hardware solutions on multi-core architectures involving caches, memory, and PCIe. Required technical skills include C++, Python, and PyTorch, with specific experience in serving frameworks like vLLM. The role addresses technical challenges in LLMs, multi-modal, and reasoning models, requiring a deep understanding of neural network operators, linear algebra, and machine learning accelerators.

Skills

PyTorch vLLM Python C++ LLMs Neural Networks Multi-core Architecture SoC Architecture Performance Modeling Machine Learning Accelerators Linear Algebra PCIe NoCs Compiler Technology

What you'll do

  • Develop software solutions for inference acceleration across the full product life cycle.
  • Plan, manage, and deliver large-scale commercial software projects.
  • Develop and optimize high-performance software for multicore systems using C++ and Python.
  • Execute, analyze, and optimize neural networks for machine learning applications.
  • Analyze software and hardware performance on multi-core architectures including cache, memory, and PCIe.
  • Perform performance modeling of SoC architectures and machine learning accelerators.
  • Implement and support serving frameworks such as vLLM.
  • Develop and optimize neural network operators and mathematical libraries.

What we're looking for

  • Bachelor's degree in a related field and 8+ years of engineering experience.
  • Master's degree in a related field and 7+ years of engineering experience.
  • PhD in a related field and 6+ years of engineering experience.
  • Proven ability of planning, managing and delivering large commercial software projects (preferred).
  • Experience in serving frameworks like vLLM, PyTorch, and writing high-performance software for multicore systems (preferred).
  • Strong understanding of LLMs, multi-modal models, and neural network operators (preferred).
  • Experience with C++, Python, and performance modeling of SoC architectures (preferred).
  • Experience with machine learning accelerators and related software is highly desired (preferred).

Related searches

More Principal SW Engineer jobs Principal SW Engineer jobs in San Diego All jobs at Qualcomm

More like this

Similar roles

Senior Staff LLM Serving Engineer

Qualcomm

San Diego, CA +1 40 days ago $162,000–$243,000
LLM Serving PyTorch Python Triton-Inference Server vLLM SGLang CUDA Triton torch.compile torchDynamo Distributed Systems Deep Learning Model Optimization KV-Cache Management Inference Acceleration KServe Ollama LMCache MoonCake
4+ yrs exp
Save

AI TLM Performance Modeling

Qualcomm

San Diego, CA 32 days ago $162,000–$243,000
Python C/C++ SystemC TLM2.0 TensorFlow PyTorch LLVM GCC SoC Architecture DDR Memory Controller NoC Design RTL DSP Architecture Machine Learning Performance Modeling
4+ yrs exp
Save

Senior Principal Software Engineer, LLM Engineering

JPMorgan Chase

Palo Alto, CA +4 64 days ago
Python AWS LLMs GNNs MLOps LLMOps PyTorch TensorFlow Hugging Face Transformers Triton Inference Server vLLM Kubernetes Docker Terraform CloudFormation CI/CD infrastructure‑as‑code SageMaker EKS MLflow Kubeflow Java Azure ML GCP Vertex AI
10+ yrs exp
Save

Lead AI Engineer

Capital One Financial

Cambridge, MA +3 140 days ago
Python Go Scala Java C++ C# PyTorch Huggingface AWS Google Cloud Azure VectorDBs Nemo Guardrails LLM Inference Similarity Search Machine Learning
4+ yrs exp
Save

Principal Software Engineer, LLM Optimization

JPMorgan Chase

Jersey City, NJ +3 61 days ago
LLM Inference vLLM TensorRT-LLM SGLang Quantization FP8 INT8 INT4 GPTQ AWQ Speculative Decoding EKS AWS KV-cache DCGM NVML ML Observability Agentic AI
7+ yrs exp
Save