Xiao Bin
A seasoned AI practitioner, former Huawei AI engineer, and technology content creator on Bilibili. He focuses on large model engineering practices and career coaching for AI job seekers.
Timeline (last 90 days)
In the training camp, Xiao Bin demonstrated an enterprise-level project that simultaneously connects to multiple large model vendors: the main reasoning model uses the DeepSeek series, the summarization model uses a lightweight version, and a Zhipu model is configured as a backup reasoning channel.
According to observations by Xiao Bin, a Bilibili uploader and instructor at Mashibing Education, requirements in large model engineer interviews for complex task handling, multi-agent collaboration and task planning have become increasingly pronounced since the second half of 2025.
According to an analysis by Bilibili creator Xiao Bin (an instructor at Mashi Bing Education, teaching Python and AI since 2021), the correct answer rate for interview questions about multi-agent architectures and the difference between Workflow and Agent is less than 1%.
Xiao Bin mentioned that domestic and international vendors have now widely support the Agent Skills standard, and the ecosystem is rapidly taking shape.
Xiao Bin is a Python and AI instructor at Mashilin Education and a technical UP host on Bilibili
According to the instructor's account, in the second half of 2025, interview intensity for AI agent positions increased, with a single interview often lasting one to two hours and more than 15 agent-related questions being asked
This project was created by Bilibili UP host Xiao Bin (Teacher Xiao) and provides complete runnable code and interface demonstrations
Since the launch of the large model course, Xiao Bin has served more than 1,700 students.
Xiao Bin has completed 625 interview debriefs.
Xiao Bin has completed 1,065 resume revisions.
1 more timeline events
All Facts (5)
According to observations by Xiao Bin, a Bilibili uploader and instructor at Mashibing Education, requirements in large model engineer interviews for complex task handling, multi-agent collaboration and task planning have become increasingly pronounced since the second half of 2025.
50%UnverifiedIn the training camp, Xiao Bin demonstrated an enterprise-level project that simultaneously connects to multiple large model vendors: the main reasoning model uses the DeepSeek series, the summarization model uses a lightweight version, and a Zhipu model is configured as a backup reasoning channel.
50%UnverifiedXiao Bin is a Python and AI instructor at Mashilin Education and a technical UP host on Bilibili
50%UnverifiedThis project was created by Bilibili UP host Xiao Bin (Teacher Xiao) and provides complete runnable code and interface demonstrations
50%UnverifiedXiao Bin is the founder of Mashi Education and previously worked at China Telecom.
50%