DevOps Engineer
Design and operate AI gateway infrastructure on cloud platforms to enable safe and efficient use of generative AI. Build, maintain, and automate core infrastructure with Kubernetes and IaC, implement CI/CD and manage the SDLC, monitor systems around the clock, respond to incidents, improve security and compliance, and optimize cloud costs through FinOps.
Responsibilities
- Design and operate AI Gateway infrastructure using AWS Bedrock, Google Vertex, Microsoft Foundry, and related cloud platforms.
- Abstract internal assets through MCP or CLI to build an Agentic AI infrastructure environment.
- Design AWS network topology and core infrastructure, and operate Kubernetes and container runtimes using IaC.
- Configure CI/CD and manage the software development lifecycle.
- Provide 24/7 on-call support, monitor infrastructure metrics and logs, and prevent or resolve incidents.
- Research and implement Zero Trust security measures and ensure compliance.
- Control and optimize infrastructure, cloud, and SaaS costs through FinOps.
- Research new tools and improve repetitive processes for developer productivity.
Requirements
- 3+ years of experience building and operating infrastructure on Amazon Web Services.
- Experience building or operating an AI Gateway or integrating LLM APIs with MCP or CLI.
- Proficiency with AI tools such as Claude Code and OpenAI Codex.
- Cloud-native mindset including self-healing, containerization, and automation.
- Experience operating Kubernetes for container orchestration.
- Experience with IaC using Terraform, Helm, and Packer.
- Experience in fintech or finance is preferred.
- Experience considering security for AWS and Kubernetes infrastructure is preferred.
- Strong communication skills with developers to identify and resolve issues.
- Willingness to learn, apply, and share new technologies.