Embedded ML Staff Engineer -- Snapdragon Mobile

Originally posted 18 October 2026 by the employer.

About the role

As a senior individual contributor on the Mobile Handset software architecture team, you will design and implement software solutions for new use-cases and features across Snapdragon Mobile products. The role focuses on evolving Snapdragon Mobile AI software by driving performance and power enhancements across SW/HW stacks for CPU, GPU, and NPU execution.

What you'll do

- Design and implement architecture for complex AI features and subsystem experiences on Snapdragon Mobile products. - Build on-device agentic experience components, including context and memory management, perception pipelines, and heterogeneous compute placement for LLM/SLM workloads across CPU, GPU, and NPU under power, thermal, and memory budgets. - Implement closed-loop, telemetry-driven resource scheduling components that dynamically re-evaluate workload placement against live power, thermal, and SLA signals. - Implement memory and model-state lifecycle management for on-device LLM/SLM serving, including KV-cache and context-state caching, eviction, paging, and reuse across sessions. - Evaluate and architect around memory bandwidth and data-movement constraints, including high-bandwidth memory and on-chip interconnects, to maximize AI throughput and efficiency. - Serve as a technical resource in design reviews, collaborate with external partners on subsystem milestones, and contribute technical input to roadmap discussions.

What you'll need

- Bachelor's degree in Computer Science, Engineering, Information Systems, or related field with 8+ years of Hardware, Software, or Systems Engineering experience (or Master's with 7+ years, or PhD with 6+ years). - Experience with Mobile SW design and deployment, system SW performance optimization, and benchmarking. - Experience with performance breakdown analysis across CPU, GPU, and NPU architectures.

Nice to have

- Proficiency in programming languages including C, C++, and Python, with familiarity in TypeScript, Java, or Kotlin. - Experience with AI frameworks (such as TensorFlow and PyTorch), foundational models, and small language models (SLMs), including LoRA/adapter-based fine-tuning and on-device personalization. - Experience with agentic AI architectures (planning, tool-use/orchestration, context and memory management) and graph-based (DAG) or state-machine-driven schedulers. - Knowledge of LLM/SLM serving internals, such as KV-cache management, paging/eviction strategies, and multi-agent resource allocation. - Understanding of memory subsystems and interconnect bandwidth (HBM/LPDDR, cache hierarchies, NPU memory architecture) and modeling AI workloads for performance and power estimation. - 5-8 years of experience in High-Performance Computing System Engineering or Software, with 2 years in AI system optimization.

Skills: Snapdragon Mobile AI software, performance and power enhancements, SW/HW stacks, CPU, GPU, NPU, LLMs/SLMs, heterogeneous compute placement