Hunyuan LLM Site Reliability Engineer

About Tencent

Tencent is an Internet-based platform company founded in Shenzhen, China, in 1998. We use technology to enrich the lives of Internet users and assist the digital upgrade of enterprises. Our mission is "Value for Users, Tech for Good". We embrace a culture of teamwork & creativity and are driven by our values - Integrity, Proactivity, Collaboration and Creativity.

We are rapidly expanding our international operations and are looking for top talent to propel us forward. Combining the results-oriented nature of a start-up with the resources of a profitable and leading Internet company, Tencent offers a unique opportunity for aspiring individuals to thrive.

Job Description

1. Responsible for the operation and maintenance of overseas model services at Hunyuan, ensuring stable, reliable, and efficient service operations;
2. Responsible for capacity management and planning, resource cost optimization, ensuring reasonable online service capacity and improving resource efficiency;
3. Responsible for continuous integration and delivery, efficient and automated operational optimization, enhancing service stability and research and development efficiency;
4. Participate in the design of online systems and various service architectures, providing professional solutions for stability and architecture improvement;
5. Analyze and deeply explore the shortcomings of existing systems, data-driven to find weak points, and promote system optimization implementation and improvement;
6. Pay attention to industry front-end technology trends, explore technologies and directions for automation and intelligence in the operation and maintenance of complex business systems.

Job Requirement

1. Bachelor's degree or above, with internship experiences in internet operations and maintenance;
2. Familiar with Linux operating system, with solid system management and network knowledge;
3. Familiar with deploying, configuring, and tuning components such as Nginx, Redis, MySQL;
4. Proficient in monitoring systems such as Zabbix, Prometheus, Grafana, real-time grasping the running status of overseas systems;
5. Proficient in at least one programming language (such as Python, Go, Shell, etc.), with experience in developing automated operational tools to meet the needs of complex and variable overseas operations and maintenance;
6. Familiar with mainstream public cloud operations and maintenance management overseas (such as AWS, Azure, etc.), with experience in containerization and microservices architecture, able to cope with the characteristics and differences of local cloud services;
7. Strong sense of work responsibility, good communication skills, learning ability, and team spirit;
8. Proficient in English and Chinese listening, speaking, reading, and writing, timely writing updated workflow and technical documents as required. Bilingualism required to work with both international stakeholders and China HQ based teammates.