The LLM Serving Engineer role at Qualcomm focuses on developing scalable LLM inference platforms and contributing to various LLM serving packages. This position is part of the Cloud AI Engineering team, which is dedicated to advancing Cloud AI technologies through innovative hardware and software solutions. Candidates will engage in the full product lifecycle, from research and development to commercial deployment, requiring strong communication and strategic thinking skills. The role also involves collaboration with internal teams and customers to drive effective solutions.

• Bachelor's degree in Computer Science, Engineering, Information Systems, or related field and 4+ years of relevant experience, or a Master's degree with 3+ years, or a PhD with 2+ years.
• Hands-on experience with LLM serving/orchestration packages such as Triton-Inference Server and vLLM.
• Deep understanding of foundational LLMs, transformer-based architectures, and experience in developing language models using PyTorch.
• Strong computer science fundamentals including algorithms, data structures, and parallel programming.
• Proficient in Python development for large-scale projects.

• Build a scalable LLM inference platform using advanced inference techniques.
• Contribute to the development of LLM Serving packages.
• Collaborate with internal teams to drive customer solutions.
• Identify new optimization opportunities by understanding advanced algorithms.
• Engage with open-source serving communities to evolve the framework.

• Qualcomm offers competitive compensation, annual bonuses, stock programs, comprehensive healthcare coverage, retirement plans, wellness programs, parental leave, flexible work options, and professional development opportunities.