Own and operate production infrastructure for ML/LLM serving systems.
Build and manage infrastructure-as-code using Terraform across GKE/Kubernetes environments.
Manage IAM, secrets, and networking configurations securely at scale.
Build and maintain CI/CD pipelines for ML and platform services.
Establish observability and autoscaling for production ML/LLM workloads.
Lead production incident management, ensuring reliability and quick recovery.
Operate as a senior hands-on IC, available to start quickly on a contract basis.
Deep hands-on experience with GKE and Kubernetes.
Solid experience with Terraform for infrastructure-as-code.
Experience managing IAM, secrets, and networking at production scale.
Proven experience building and maintaining CI/CD pipelines.
Robust background in observability and autoscaling practices.
Experience serving ML/LLM workloads in production.
Demonstrated production incident management experience.

📌 Senior Ml Platform Engineer Bengaluru (India)
🏢 Tavant Technologies
📍 India