微信-后台开发高级工程师-机器学习工程方向
Core
Research and develop AI model inference acceleration technologies for WeChat business scenarios, optimizing TFCC service platforms and inference engines to enhance performance for recommendation, large language, and traditional models.
Role type
Senior Machine Learning Infrastructure Engineer
Builds
TFCC service platform, inference engines, and optimized AI algorithms for voice recognition, synthesis, visual understanding, and LLMs
Domain
Internet / AI Infrastructure / Model Inference
Deliverable
production ML models
Required skills
C/C++, Linux development, data structures and algorithms, model inference optimization, backend engineering
Preferred skills
AI architecture design, latest AI technology trends, performance tuning
Technologies
TFCC, inference engines, large language models, voice recognition, visual understanding
Responsibilities
Research and apply AI model inference acceleration techniques; Develop and optimize backend AI algorithms for various business scenarios; Follow AI trends to upgrade internal technical solutions and platform architecture.
