Software Engineer

Job Title: Software Engineer – AI/ML Infrastructure

Location: Taipei, Taiwan

Contract: Long-term Contract

Job Description:

We are looking for a Software Engineer to troubleshoot and optimize large-scale AI workloads, including LLM deployment, distributed training, and inference performance on TPU/GPU infrastructure.

Key Responsibilities:

• Debug complex technical issues and perform root-cause analysis.
• Deploy and optimize LLMs using JAX, PyTorch, or vLLM.
• Optimize distributed training, inference, latency, and throughput.
• Troubleshoot Kubernetes/GKE clusters and AI infrastructure.
• Collaborate with global engineering teams to improve system performance and reliability.

Requirements:

• Bachelor's or Master's degree in Computer Science or a related field.
• Strong Python and/or C++ programming skills.
• Experience in complex troubleshooting and distributed systems.
• Knowledge of Kubernetes/GKE, LLMs, and GPU/TPU infrastructure is preferred.
• Familiarity with performance profiling tools such as NCCL, DCGM, or XLA Profiler is an advantage.