On-Device AI Engineer: Co-Design & Deployment
Posted Updated
Description
Lenovo Group Limited is seeking a research-engineering expert to translate frontier on-device AI research into reliable solutions. You will optimize models for NPU/GPU/CPU, drive cross-team integration, and build the infra to accelerate experimentation.
The role emphasizes end-to-end project management, collaboration with engineering, product, and hardware teams, and establishing reusable toolchains and standards. PhD is preferred for top candidates.
Turn frontier research into on-device engineering solutions that run reliably on device. Own model adaptation, performance optimization, and integration delivery. Work with chip and system teams on heterogeneous on-device hardware for inference. Build and maintain training and inference infrastructure to speed up research iteration. Manage projects end to end, plan milestones, and ensure on-time delivery. Bridge research with engineering, product, and hardware teams to close cross-team issues. Master's degree or above in CS/AI/EE/Math; PhD preferred; 3+ years research experience. Strong fundamentals in deep learning and large models; Transformer familiarity. Experience in architecture design, hardware-software co-design, or efficient training/inference. Strong research fundamentals; independent problem solving; comfortable with frontier exploration. Proficiency in Python and PyTorch with hands-on model training experience.Skills
Sign in to read and join the discussion.