AI Platform Engineer

Job Overview:

The AI Platform Engineer builds, hardens, and helps operate the enterprise GenAI/agentic platform that enables teams to safely develop and run AI agents at scale. This role owns the platform “foundations”—including LLM gateway & model routing, vector/knowledge base infrastructure, CI/CD and IaC automation, observability, and cost/usage management across use cases —so Dev teams can deliver agents quickly under consistent governance and controls. This role focuses on shared platform capabilities (as distinct from use-case AI engineering) and partners closely with CoE product/ops enablement and governance stakeholders to keep the platform scalable, compliant, and easy to onboard new agents and tools.

Key Responsibilities:

• Engineer and maintain the platform’s foundational capabilities: LLM gateway, model routing, shared compute/infrastructure, and platform governance controls.
• Onboard and support new platform capabilities and tools used by agents (e.g., adding/maintaining supported models and agent tooling standards).
• Provision and manage platform resources needed to scale agent development (e.g., provisioning Bedrock Knowledge Bases/vector-backed retrieval components where applicable).
• Build and maintain Terraform (or equivalent) IaC to create/update platform resources and dashboards; keep deployments repeatable across environments.
• Own and operate platform pipelines: executing Terraform + backend/frontend pipelines, troubleshooting failed deployments, and improving delivery reliability.
• Provide “platform support” for agent teams by diagnosing platform-related issues (e.g., deployment/update failures, agent creation problems, missing/incorrect results, conversation memory issues).
• Implement and maintain monitoring for performance/quality and agent behavior over time (including benchmark testing and evaluation monitoring such as “Bedrock Eval” where applicable).
• Own platform cost & usage management practices (budget signals, usage metrics, reporting, optimization recommendations).
• Collaborate with Security/Architecture/Governance partners to ensure platform controls align to enterprise policies and approved operating patterns (e.g., access controls, safe enablement of who can create what kinds of agents).

Required Qualifications:

• Bachelor’s degree in computer science, Engineering, Information Systems, or related technical discipline, or equivalent experience.
• Demonstrated experience designing and operating shared application or platform services in an enterprise environment.
• Experience with CI/CD pipelines, automation, and infrastructure provisioning.
• Working knowledge of modern AI/ML or GenAI platforms and cloud-based services.
• Strong understanding of operational reliability, monitoring, and support practices.
• Experience supporting AI, ML, or GenAI 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, or FinOps practices.
• Professional cloud or AI-related certifications (AWS, Azure, or equivalent).

Benefits:

• Flexible remote work environment.
• Comprehensive health benefits and wellness programs.
• Opportunities for professional development and career growth.

Company Culture:

At Cinteot, we foster an inclusive and collaborative environment where innovation thrives. We believe in empowering our employees to take ownership of their work and contribute to meaningful projects that impact our community and industry.