The AI Performance Engineer role at Qualcomm focuses on optimizing and deploying models for efficient inference within the Cloud AI Engineering team. This position involves working on cutting-edge research and development, as well as commercial deployment of AI solutions. The ideal candidate will engage in performance analysis and optimization of various AI models while collaborating closely with internal teams and customers. Strong communication and problem-solving skills are essential for success in this dynamic and collaborative environment.

• Bachelor's degree in Computer Science, Engineering, Information Systems, or related field and 6+ years of relevant work experience, or a Master's degree and 5+ years of experience, or a PhD and 4+ years of experience.
• Hands-on experience in building and optimizing language models, particularly in PyTorch and ONNX.
• Deep understanding of transformer architectures and attention mechanisms.
• Strong Python programming skills.
• Understanding of computer architecture, ML accelerators, and distributed systems.

• Convert, optimize, and deploy models for efficient inference using PyTorch and ONNX.
• Analyze complex performance or stability issues to identify root causes.
• Create engineering solutions to provide continuous insights into AI workload performance.
• Design and implement high-level kernels with a focus on generating efficient, low-level code.
• Collaborate with internal compiler, firmware, and platform teams to drive solutions.

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