Machine Learning Engineer

Skip to main contentOur CompanyOur BusinessSearch for JobsJoin Talent NetworkFAQsProfileEnglishSign InSingle PositionView All JobsMachine Learning EngineerGuangdong, China +1 moreNo longer accepting applications.Job ID3092630Detailed Project Description1. Focus on the design and implementation of key modules for the Generative AI inference runtime (Genie), enabling efficient execution of complex models on edge and embedded platforms.2. Implement and optimize inference for large language models (LLMs) and multimodal models on embedded and edge platforms, including improvements in execution efficiency, memory management, and resource utilization.3. Design and optimize collaboration mechanisms between the inference runtime and Qualcomm chipsets, enhancing overall system performance and scalability.4. Resolve system‑level performance and stability issues within Generative AI platforms.5. Collaborate across teams to drive the adoption of Generative AI inference technologies in platform‑level use cases.Skills / Experience Required 1. Deep understanding of LLM / LVM inference execution workflows, with system‑level design and implementation experience.2. Proficient with Android / Linux development environments, with hands‑on experience on embedded or heterogeneous computing platforms.3. Familiar with performance, memory, and concurrency optimization techniques in resource‑constrained environments.4. Expert‑level proficiency in C++, with solid experience using Python and/or Java in system or AI engineering contexts.5. Long‑term ownership experience with AI inference runtimes, AI acceleration technologies, or platform‑level components is a strong plus.6. Experience with Qualcomm NPU deployment and development is highly preferred.