Description

Key Skills: Google Cloud Platform, Terraform, Kubernetes, Docker, Python, Bash, CI/CD, Infrastructure as Code, Vector Databases, DevSecOps

Good to Have Skills: Experience with GKE, Cloud Run, Vertex AI, GCS, NEG, Pinecone, Weaviate, ElasticSearch, Vertex Search, Cloud Monitoring, LLM metrics monitoring, UNIX/Ubuntu systems, networking protocols, security architectures, IAM principles, Ansible, automation mindset, complex systems analysis, mentoring abilities.

Roles & Responsibilities:

• Own Helpshift production services and ensure complete monitoring coverage, troubleshoot and fix production issues.
• Design and maintain scalable GCP infrastructure using Terraform for Infrastructure as Code implementation.
• Build deployment pipelines for AI agents, managing vector databases and model endpoints for AI orchestration.
• Implement Security-by-Design including IAM least-privilege access, secret management, and automated vulnerability scanning for AI workloads.
• Architect high-velocity CI/CD pipelines for both traditional microservices and AI model prompts and configurations.
• Set up comprehensive monitoring for system health and LLM-specific metrics including latency, token usage, and cost.
• Optimize GCP costs and manage resource quotas, especially for GPU/TPU-intensive AI tasks for cloud governance.
• Establish and optimize connectivity among applications deployed in different cloud environments like AWS and GCP.

Experience Required: 6+ years of relevant experience with expert-level Google Cloud Platform administration skills, experience with vector databases, containerization technologies, and proficiency in designing highly scalable, fault tolerant and cost-effective solutions

Key Skills

Education

Any Graduate