岗位职责：负责大模型训练和推理服务的优化、性能提升、加速、动态扩展和容错稳定性研究如何实现并工程落地已知的算法、原理或需求及方案跟踪并改进业界开源方案与内部团队配合，按照计划完成进度要求的方案实现支持或与其他团队协作，配合完成线上环境部署负责生产线上环境的支持、故障分析和解决Requirements:Responsible for the optimization, performance improvement, acceleration, dynamic scaling and fault-tolerant stability of large model training and inference servicesStudy how to implement and engineering the known algorithms, principles or requirements and solutions.Track and improve industry open source solutionsCooperate with internal teams to complete the implementation of solutions according to the schedule requirementsSupport or collaborate with other teams to complete online environment deploymentResponsible for the support, fault analysis and resolution of the production line environment
岗位职责：
Want more jobs like this?GetScience and EngineeringjobsinHangzhou, Chinadelivered to your inbox every week.
Want more jobs like this?
GetScience and EngineeringjobsinHangzhou, Chinadelivered to your inbox every week.
Get Jobs
