Taro Logo

Cloud Machine Learning LLM Serving Staff engineer

A global technology company developing hardware and software for Machine Learning solutions spanning data center, edge, infrastructure, and automotive markets.
Machine Learning
Staff Software Engineer
In-Person
5,000+ Employees
8+ years of experience
AI · Enterprise SaaS · Automotive

Description For Cloud Machine Learning LLM Serving Staff engineer

Qualcomm's Cloud Computing team is seeking a Staff Engineer to join their Machine Learning division, focusing on developing cutting-edge hardware and software solutions across data center, edge, and automotive markets. This role combines technical leadership with hands-on development, requiring expertise in deep learning, LLMs, and high-performance computing. The position offers an opportunity to work with state-of-the-art AI technologies and lead teams in developing innovative solutions.

The role involves optimizing deep learning models, building framework extensions, and working with technologies like vLLM, Triton, and TorchDynamo. The ideal candidate will have extensive experience in software engineering, particularly with C++ and Python, along with a strong foundation in mathematical modeling and machine learning algorithms.

Qualcomm offers a comprehensive benefits package including world-class health coverage, financial planning support, and professional development opportunities. The company culture emphasizes innovation, collaboration, and professional growth, making it an ideal environment for ambitious engineers looking to make an impact in the AI/ML space.

Working at Qualcomm means joining a global leader in technology innovation, with opportunities to work alongside industry experts and contribute to breakthrough technologies that impact lives worldwide. The position offers both technical challenges and leadership opportunities, perfect for experienced engineers looking to advance their careers in machine learning and AI development.

Last updated 2 months ago

Responsibilities For Cloud Machine Learning LLM Serving Staff engineer

  • Analyze software requirements and determine design feasibility within constraints
  • Lead high performing teams towards system design and deliverables
  • Improve and optimize key Deep Learning models on Qualcomm AI 100
  • Build deep learning framework extensions for Qualcomm AI 100
  • Work on vLLM, Triton, ExecuTorch, Inductor, TorchDynamo
  • Optimize workloads for both scale-up and scale-out systems
  • Optimize the entire deep learning pipeline including graph compiler integration

Requirements For Cloud Machine Learning LLM Serving Staff engineer

Python
  • Bachelor's/Masters/PhD degree in Engineering, Machine learning/AI, Information Systems, Computer Science, or related field
  • 8+ years Software Engineering or related work experience
  • 8+ years experience with Programming Language such as C++, Python
  • Deep Learning experience or knowledge – LLMs, NLP, Vision, Audio, Recommendation systems
  • Knowledge of Pytorch, TensorFlow software stacks
  • Excellent C/C++/Python programming and software design skills
  • Experience in using C++ 14 (advanced features)
  • Well versed with open-source development practices

Benefits For Cloud Machine Learning LLM Serving Staff engineer

Medical Insurance
Education Budget
  • World-class health coverage for employees and dependents
  • Financial planning and future preparation programs
  • Emotional/mental strength support
  • Wellbeing programs
  • Tuition reimbursement
  • Mentorship programs

Interested in this job?

Jobs Related To Qualcomm Cloud Machine Learning LLM Serving Staff engineer