Staff/Sr. ML Infrastructure / Platform Engineer

Join Trend ‧ Join New Generation

趨勢科技 - 全球雲端資安領航者 / 全亞洲最大軟體公司 / 企業版圖橫跨五大洲 / 趨勢全球研發基地在台灣 
===============================================================

About the Role 

We are building a production-grade, GPU-accelerated LLM serving platform that powers multiple AI products at enterprise scale. You will be responsible for designing, building, and operating the infrastructure that serves large language models — from raw Kubernetes cluster management to multi-GPU inference optimization and autoscaling. 

Required Qualifications 

Model Serving & Inference 

• Operate multi-model LLM serving infrastructure 

• Tune autoscaling policies to balance GPU cost and latency SLAs 

Kubernetes & GPU Infrastructure 

• Operate production K8s clusters with NVIDIA GPU nodes 

• Handle GPU node lifecycle: NVIDIA driver setup 

Infrastructure as Code 

• Write and maintain Terraform/Terragrunt modules for AWS/GCP cloud 

• Package platform components and model deployments as Helm charts 

• Manage multi-environment configurations 

Observability & Performance 

• Maintain monitoring stack: Prometheus, Grafana, 

• Build dashboards for GPU utilization, KV cache occupancy, TTFT/ITL latency, and cost per token 

• Set up alerting for SLA violations and OOM events 

Bonus Skills 

These are not required, but candidates with these skills will stand out. 

• LoRA / PEFT fine-tuning workflows 

• MLflow for experiment tracking, model registry, and automated adapter deployment 

• Experience building LoRA adapter CI/CD pipelines (training → registry → serving) 

• Experience with alternative inference frameworks such as SGLang or NVIDIA NIM, including deep Parameter Tuning for Continuous Batching, KV Cache management, and Speculative Decoding. 

===============================================================
連結智慧 守護世界 --- Connected Intelligence for Securing a Connected World