Software Engineer II - GPU/AI Infrastructure

About the role

Tencent Overseas IT builds the global IT platforms, applications and services that support Tencent's worldwide growth. This Software Engineer II role focuses on GPU and AI infrastructure, working with algorithm and business teams to make AI workloads more efficient.

Key responsibilities

• Design, develop and deliver GPU/AI infrastructure platforms and tools
• Build core capabilities for GPU resource management, workload scheduling, distributed training and inference
• Develop and improve the engineering infrastructure around mainstream AI frameworks and runtimes for LLM workloads
• Optimize GPU cluster performance, stability and resource utilization
• Work closely with algorithm and business teams to solve AI workload engineering challenges

Required profile

• Strong software engineering skills in Python, Go or C++
• Solid understanding of Linux, Docker and Kubernetes
• Familiarity with GPU technologies such as CUDA, NCCL and RDMA
• Experience with distributed systems or distributed computing
• Experience with AI coding or AI agents, or AI-assisted software development
• Experience in LLM training, inference or GPU cluster infrastructure is a plus