GenAI GCP Platform Engineer

Arkhya Tech Inc.; Austin (TX); On-site; USD 150,000 - 210,000; Full time

Job summary

Arkhya Tech Inc. is seeking two GenAI Platform Engineers to build and operate a scalable platform on Google Cloud, enabling Gemini, Vertex AI, and Model Garden models for internal teams. You will manage endpoints, IAM, networking, and capacity using Terraform, and own the model lifecycle with production support.

Ideal candidates bring hands-on GCP AI experience, Terraform proficiency, and a strong focus on cost governance and security controls to ensure reliable, cost-efficient AI services.

Qualifications

• Experience with Google Cloud AI and LLM services (Vertex AI, Gemini, Model Garden)
• Proficient with Terraform and Infrastructure as Code, creating reusable modules
• Experience managing model endpoints, IAM, VPC networking, quotas, and GPU capacity on GCP
• Experience with production systems monitoring and incident response
• Understanding of cloud cost tracking, governance, and security controls

Responsibilities

• Enable and operate Gemini, Vertex AI, and Model Garden models for internal teams
• Enable open-weight and partner models through Vertex AI Model Garden, including quotas and GPU requests
• Build and maintain Terraform modules for model enablement, endpoints, IAM, and networking
• Manage the full model lifecycle: version upgrades, deprecations, and migrations with minimal disruption
• Provide production support for enabled models, including monitoring, incident triage, and escalation to Google support
• Track model usage and cost by consuming team
• Follow and enforce security, access, and governance controls

Skills

Vertex AI

Model Garden

Gemini

Terraform

IAM & Networking

GPU capacity on GCP

Monitoring & incident response

Cost governance

Tools

Terraform

Job description

Location: Austin, TX (Onsite)

About the Role

We’re hiring two GenAI Platform Engineers to enable and operate large language models on Google Cloud. You’ll build the platform that makes Gemini, Vertex AI, and Model Garden models available to internal teams, using Terraform to manage endpoints, access, networking, and capacity. You’ll also own the model lifecycle and provide production support for the models you enable.

Key Responsibilities

• Enable and operate Gemini, Vertex AI, and Model Garden models for consuming teams
• Enable open-weight and partner models through Vertex AI Model Garden (Model-as-a-Service and self-deployed), including quota and GPU capacity requests
• Build and maintain reusable Terraform modules for model enablement, endpoints, IAM, and networking
• Manage the full model lifecycle: version upgrades, deprecations, and migrating consuming teams to newer versions with minimal disruption
• Provide production support for enabled models, including monitoring, incident triage, and escalation to Google support when needed
• Track model usage and cost by consuming team
• Follow and enforce security, access, and governance controls

Required Skills

• Strong hands-on experience with Google Cloud AI and LLM services, including Vertex AI, Model Garden, and Gemini
• Proficiency in Terraform and Infrastructure as Code, with experience building reusable modules
• Experience managing model endpoints, IAM, VPC networking, quotas, and GPU capacity on GCP
• Experience supporting production systems: monitoring, incident response, and vendor escalation
• Understanding of cloud cost tracking, governance, and security controls