DNN Model optimization Expert Engineer
Core
Design and implement a neural acceleration platform for on-device execution of GenAI LLM/LVM models, optimizing inference and training on mobile SoCs.
Role type
Senior IC DNN Model optimization Expert Engineer
Builds
Accelerated on-device ML inference & training platform for mobile devices
Domain
Mobile AI, Deep Learning, System-on-Chip (SoC) optimization
Deliverable
production ML models
Required skills
Model optimization (compression, quantization), Neural architecture search, LLM/LVM on-device expertise, Python, C++, Linux, PyTorch/TensorFlow/AI-Edge, Multi-threading/Multicore programming, ARM processor architecture knowledge
Preferred skills
Distributed computing, Compiler development, Low-level optimizations, Research publications & patents
Responsibilities
Design and develop machine learning algorithms for mobile use cases, Lead design of neural acceleration platform, Ensure high-quality code delivery, Refine work backlog with product owners and managers, Identify opportunities to leverage existing platform capabilities
Seniority
Senior, hands-on IC
