Machine Learning Engineer
Core
Design and optimize Generative AI inference runtimes (Genie) for efficient execution of LLMs and multimodal models on edge and embedded platforms.
Role type
Senior IC machine learning engineer (edge inference)
Builds
Generative AI inference runtime (Genie) and optimized inference for LLMs/multimodal models on Qualcomm chipsets
Domain
Embedded systems / Edge AI / Generative AI
Deliverable
production ML models
Required skills
C++, Python, Java, LLM inference workflows, embedded systems development, Android/Linux development, performance optimization, memory management, concurrency optimization
Preferred skills
AI inference runtime ownership, AI acceleration technologies, Qualcomm NPU deployment
Technologies
C++, Python, Java, Android, Linux, Qualcomm NPU, Genie runtime
Responsibilities
Design and implement key modules for the Generative AI inference runtime (Genie). Implement and optimize inference for large language models (LLMs) and multimodal models on embedded and edge platforms. Design and optimize collaboration mechanisms between the inference runtime and Qualcomm chipsets. Resolve system-level performance and stability issues within Generative AI platforms. Collaborate across teams to drive the adoption of Generative AI inference technologies in platform-level use cases.
