Description

You will deploy and manage machine learning models within Kubernetes-based production environments. You own the lifecycle of model serving, from configuration to observability.

Responsibilities

• Deploy and configure Kubernetes components including API Gateway, Ingress, Model Serving, Logging, Monitoring, and Cron Jobs.
• Administer Kubernetes clusters across cloud (EKS, GKE, AKS) or on-prem environments (native Kubernetes, Gravity, MetalK8s).
• Manage cluster networking and Linux host networking to ensure stable model inference.
• Implement MLOps workflows using automation, monitoring, and configuration management platforms.
• Utilize observability tools to maintain system health and troubleshoot production issues.

Required Skills

• 2+ years of experience in machine learning or related roles.
• Proficiency in Python, Node, Go, or Bash.
• Hands-on experience with Seldon Core, MLFlow, Istio, Jaeger, Ambassador, Triton, PyTorch, and TensorFlow/TFserving.
• Experience with distributed computing and deep learning technologies including Apache MXNet, CUDA, cuDNN, and TensorRT.
• In-depth knowledge of Docker and Kubernetes administration.
• Experience with observability tools such as Splunk, Prometheus, and Grafana.
• Practical experience with ML, Python, and Seldon.

Preferred Skills

• Background in MLOps and automation platforms.

Key Skills

Education

ANY GRADUATE