Volcano Ark Large Model Platform - Operation and Maintenance Development Engineer

1. Design, implement and maintain a highly available and high-performance Doubao large model service architecture 2. Use Terraform and other IaC tools to manage and automate cloud infrastructure deployment 3. Develop and optimize automated operation and maintenance tools to improve model deployment efficiency and system reliability 4. Optimize the infrastructure for large-scale distributed model training and inference 5. Work closely with the AI research team to ensure the smooth deployment and stable operation of new models and functions 6. Use Terraform to manage multi-cloud environments to ensure the consistency and repeatability of infrastructure.

1. Bachelor degree or above, computer-related major, more than 3 years of development or stability construction experience in cloud computing or large models 2. Proficient in one of Python/Golang/Java, and have cloud-native related technology stack. Bonus points: 1. Understand the best practices for machine learning model deployment and servitization 2. Have experience working in a multi-cloud environment (such as AWS, GCP, Azure) 3. Familiar with CI/CD processes, and have experience using tools such as Jenkins, GitLab CI 4. Have operation and maintenance experience related to large language models or other large AI models.