← Back to list

Job
· Principal
LLM Serving Engineer (Cloud AI Engineering), Senior / Staff
AI / ML Engineer
• Principal
• On-site
• Full-time
•
San Diego, USA
Qualcomm's Cloud AI team develops hardware and software solutions for inference acceleration. The LLM Serving Engineer builds a scalable LLM inference platform, spanning the full product lifecycle from research and development to commercial deployment.
Responsibilities
- ▹Build a scalable LLM inference platform (disaggregated serving, KV-cache management, advanced parallelism, speculative algorithms, model optimization, specialized kernels).
- ▹Contribute to LLM serving packages (vLLM, SGLang, TGI, Triton Inference Server, Dynamo, LLM-d).
- ▹Work closely with customers and internal compiler, firmware and platform teams.
- ▹Understand advanced algorithms (attention mechanisms, MoEs) and numerics to identify optimization opportunities.
- ▹Drive efficient serving through smart autoscaling, load balancing and routing.
- ▹Engage with open-source serving communities to evolve the framework.
Requirements
- ▹Bachelor's degree in Computer Science, Engineering, Information Systems or related field and 4+ years of experience (or Master's + 3 years, or PhD + 2 years).
- ▹MS in Computer Science, Machine Learning, Computer Engineering or Electrical Engineering.
Nice to have
- ▹Hands-on experience with LLM serving/orchestration packages (Triton Inference Server, vLLM, SGLang, Ollama, llm-d, KServe, LMCache, MoonCake).
- ▹Deep understanding of foundational LLMs, VLMs, SLMs, and transformer-based architectures.
- ▹Strong experience developing language models with PyTorch.
- ▹Strong computer science fundamentals: algorithms, data structures, parallel and distributed programming.
- ▹Understanding of computer architecture, ML accelerators, in-memory processing and distributed systems.
- ▹Strong Python development skills for large-scale projects.
- ▹Experience analyzing, profiling and optimizing deep learning workloads.
- ▹Open-source contributions to any GenAI package.
- ▹Experience architecting and developing large-scale distributed systems.
- ▹High-level kernel design experience (PyTorch, CUDA, Triton).
- ▹Knowledge of torch.compile or torchDynamo.
- ▹PhD in Computer Science, Computer Engineering or Machine Learning.
Soft skills
Excellent communication and problem-solving skills.Thriving in a fast-paced, collaborative environment.Proactive learning about the latest inference optimization techniques.
What we offer
- ▹Annual discretionary bonus program.
- ▹Annual RSU grants.
- ▹Competitive benefits package.
About the company
Qualcomm is applying its traditional strengths in digital wireless technology to play a central role in the evolution of Cloud AI, developing hardware and software solutions for inference acceleration.
Education: Számítástechnika, informatika, mérnöki vagy villamosmérnöki alapszak (MSc előny).
Similar jobs

Job
· Principal
Staff Machine Learning Engineer
Zscaler
AI/MLHuggingfaceLlm
+3
$152,000–$190,000/yr
gross
🏢 On-site
Bellevue
🗣️ EN
Job
· Principal
Principal Machine Learning Engineer, Matching and Recommendations
Bumbleinc
AI/MLData ScienceLlm
+3
$345,000–$410,000/yr
gross
🌍 Remote
US TX Austin
🗣️ EN

Job
· Principal
Senior Staff Engineer, Machine Learning Engineering ( On-device SW )
Qualcomm
AI/MLCppLlm
+1
$194,400–$291,600/yr
gross
🏢 On-site
San Diego
🗣️ EN

Job
· Principal
Staff Machine Learning Engineer (Modeling), Support
Block
AI/MLLlm
💰 Salary: not specified
🏢 On-site
Seattle
🗣️ EN

Job
· Principal
Staff AI Engineer - US
Typeform
AI/MLDatadogData Science
+13
$170,000–$210,000/yr
gross
🌍 Remote
United States (Remote)
🗣️ EN

Job
· Principal
Staff Machine Learning Engineer(Platform - Identity)
Coinbase
AI/MLLlm
$218,025–$256,500/yr
gross
🌍 Remote
🗣️ EN