AI Platform Engineer

Role Overview

The AI Platform Engineer builds, hardens, and helps operate Cinteot’s enterprise GenAI/agentic platform. The role owns the platform “foundations” (shared capabilities like LLM gateway/routing, vector/knowledge base infrastructure, CI/CD + IaC automation, observability, and cost/usage management) so teams can develop and run AI agents safely, at scale, with consistent governance.

Responsibilities

• Engineer and maintain platform foundations:
  • LLM gateway and model routing
  • Shared compute/infrastructure
  • Platform governance controls
• Onboard and support new platform capabilities and agent tools:
  • Add/maintain supported models
  • Enforce/standardize agent tooling standards
• Provision and manage scaling platform resources:
  • Create/manage vector/knowledge base retrieval components (e.g., where applicable)
  • Use managed services to support agent development
• Build and maintain Terraform (or equivalent) IaC:
  • Create/update platform resources and dashboards
  • Keep deployments repeatable across environments
• Own platform pipelines and delivery reliability:
  • Execute Terraform + related backend/frontend pipelines
  • Troubleshoot failed deployments and improve reliability
• Provide platform support to agent teams:
  • Diagnose deployment/update issues
  • Help with agent creation problems
  • Troubleshoot missing/incorrect results and conversation memory issues
• Implement monitoring and evaluation:
  • Monitor performance/quality and agent behavior over time
  • Benchmark testing and evaluation monitoring (e.g., Bedrock Eval where applicable)
• Own cost & usage management practices:
  • Budget signals, usage metrics, reporting
  • Provide optimization recommendations
• Collaborate with Security/Architecture/Governance stakeholders to align controls to enterprise policy

Required Qualifications

• Bachelor’s degree in CS/Engineering/IS (or equivalent experience)
• Experience designing and operating shared enterprise platform/application services
• Experience with CI/CD, automation, and infrastructure provisioning
• Working knowledge of modern AI/ML or GenAI platforms and cloud-based services
• Strong operational reliability, monitoring, and support background
• Experience supporting GenAI/AI platforms in regulated industries (e.g., healthcare, insurance, financial services)
• Familiarity with agent-based architectures, LLM model integration, and AI platform patterns
• Experience with cloud cost management / usage monitoring / FinOps
• Professional cloud or AI certifications (e.g., AWS, Azure, or equivalent)

Nice-to-Haves (implicit from role)

• Familiarity with LLM evaluation/benchmark tools such as Bedrock Eval
• Experience working with governance/access control patterns for safe agent enablement