about the job.
1. Responsible for the technology evolution roadmap of the large model inference platform, and ensure that the platform can adapt to the rapidly changing AI technology trends.
2. Design and optimize the architecture of the large model inference platform, including but not limited to model deployment, inference optimization, resource scheduling, etc., to support large-scale and high-performance AI applications.
...
3. Lead the technical team to explore and implement the latest AI inference techniques, such as model compression, quantization, parallel computing, etc., to improve the performance and efficiency of the platform.
4. Work with cross-functional teams, including R&D, product and business teams, to ensure that technology solutions are aligned with company strategy and market needs.
5. Guide and cultivate team members to enhance the team's technical ability and innovative thinking.
skills and experience required.
1. Master degree or above in computer science, artificial intelligence or related field, with profound theoretical foundation and practical experience in AI.
2. Able to deeply understand and analyze the latest research results in the field of AI, and have unique insights and in-depth research on large model reasoning technology.
3. Have at least 5 years of AI framework or related system architecture design experience, familiar with mainstream AI frameworks and technologies.
4. Excellent technical leadership, able to lead the team to solve complex technical problems and promote technological innovation.
5. Have good communication and coordination skills, and can effectively communicate with team members from different backgrounds.
