Embedded ML Staff Engineer

What you'll do

• Design and implement architecture for complex AI features and experiences within Snapdragon Mobile products.
• Build hands-on prototypes and research requirements to define new AI features.
• Implement on-device agentic experience components including context management and heterogeneous compute placement for LLM/SLM workloads.
• Develop closed-loop, telemetry-driven resource scheduling components for CPU, GPU, and NPU.
• Implement memory and model-state lifecycle management for on-device LLM/SLM serving under tight memory budgets.
• Architect solutions to overcome memory bandwidth and data-movement constraints to maximize AI throughput.
• Provide technical input for design reviews and contribute to roadmap discussions with leadership.
• Collaborate with external partners on subsystem implementation plans and milestones.

What we're looking for

• Bachelor's degree with 8+ years of experience, Master's with 7+ years, or PhD with 6+ years in Engineering or related fields.
• Experience with Mobile SW design, system performance optimization, benchmarking, and performance breakdown analysis for CPU, GPU, and NPU.
• Proficiency in programming languages such as C, C++, and Python.
• Experience with embedded ML at the system level, including model deployment and lifecycle management on resource-constrained devices (preferred).
• Experience with LLM/SLM serving internals, including KV-cache management and paging strategies (preferred).
• Experience with agentic AI architectures and heterogeneous compute placement for ML workloads (preferred).
• Knowledge of AI frameworks like TensorFlow or PyTorch and state-of-the-art AI in Computer Vision, Audio, or Generative AI (preferred).
• Strong written and verbal communication skills to articulate complex technical concepts to various stakeholders.