Perks & benefits

Relocation AllowanceHealth InsuranceEducation AllowanceAnnual LeavePaid Leave

Requirements

5+ years infrastructure experience, GPU infrastructure expertise, Kubernetes proficiency, Python or Go skills, Model serving experience

KubernetesPythonGoMLOps

Design and operate an on-prem AI platform for deploying and scaling models across multi-node GPU clusters and Kubernetes
Collaborate with infrastructure teams on GPU server configuration, high-performance networking, and RDMA-enabled clusters
Manage GPU MIG configurations and ensure reliable GPU operations in Kubernetes
Design, deploy, and maintain model serving runtimes including vLLM, ONNX, SGLang, Nvidia Triton, and KServe
Build and maintain CI/CD pipelines and tooling for model packaging, versioning, and deployment
Maintain platform tooling for model lifecycle management using systems like MLflow
Enable infrastructure for model fine-tuning and adaptation such as LoRA
Develop internal tooling for managing model inputs and configurations
Conduct performance testing and observability for GPU clusters and model workloads
Evaluate and benchmark model inference performance across different runtimes and hardware

Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field
5+ years of experience in infrastructure, platform engineering, or distributed systems
Hands-on experience with GPU infrastructure (NVIDIA or AMD stack)
Strong experience with Kubernetes and production workloads
Proficiency in Linux-based environments
Strong programming skills in Python and/or Go
Experience with model serving and inference systems (vLLM, ONNX, SGLang, Triton, KServe)
Experience with CI/CD pipelines and automation
Experience with monitoring and observability tools
Proficiency in English