Embedded ML SW Architect

What you'll do

• Develop high-level architectures for complex AI features and experiences on Snapdragon Mobile products.
• Architect on-device agentic experiences including context management, perception, and heterogeneous compute placement for LLM workloads.
• Design closed-loop, telemetry-driven resource scheduling for CPU, GPU, and NPU based on live power and thermal signals.
• Design memory and model-state lifecycle management for on-device LLM serving, including KV-cache and paging strategies.
• Evaluate and architect around memory bandwidth and data-movement constraints to maximize AI throughput on constrained silicon.
• Conduct independent research and hands-on prototype development to define technical requirements for new use-cases.
• Serve as a technical expert to identify industry trends and define long-term strategic product roadmaps.

What we're looking for

• Bachelor's degree in Computer Science, Engineering, Information Systems, or related field and 8+ years of relevant engineering experience.
• Master's degree in Computer Science, Engineering, Information Systems, or related field and 7+ years of relevant engineering experience.
• PhD in Computer Science, Engineering, Information Systems, or related field and 6+ years of relevant engineering experience.
• Proficiency in programming languages such as C, C++, and Python.
• Strong written and verbal communication skills to articulate complex technical concepts to various stakeholders.
• Strong leadership abilities to motivate and guide development teams.
• Experience with large language models, small language models, and AI frameworks like TensorFlow or PyTorch (preferred).
• Experience with agentic AI architectures and embedded ML on resource-constrained devices (preferred).