Agent & DevOps Platform Engineer

Job summary

Design and maintain AWS-based developer platforms and scalable CI/CD pipelines. Develop and integrate AI/LLM-based agents and tools into enterprise developer environments using Python.

Job details

We are looking for an Agent & DevOps Platform Engineer to join our team in Toronto, ON (Onsite). The ideal candidate will have strong hands-on experience in AWS, Python, CI/CD, Kubernetes, Docker, Infrastructure as Code, and DevSecOps, along with practical experience building or integrating AI/LLM-based tools and agents. The role involves developing secure, scalable, and reusable cloud-native platforms, automation, pipelines, and AI-powered developer solutions in an enterprise environment. Key Requirements 3–5+ years of experience in DevOps, cloud, CI/CD, or platform engineering. Strong Python programming skills for automation, APIs, infrastructure tooling, and scripting. Experience with AWS production environments. Strong knowledge of AWS IAM, including roles, policies, trust relationships, cross-account access, and least privilege. Hands-on experience with Docker and Kubernetes, EKS, or ECS. Strong experience with CI/CD, Git workflows, build automation, and release pipelines. Experience with Infrastructure as Code, such as Terraform, CloudFormation, or AWS CDK. Experience building or integrating AI/LLM tools, agents, or developer platforms. Understanding of LLMOps, including prompt management, tool use, agent architecture, evaluation, observability, and reliability. Experience with cloud-native deployments and DevSecOps practices. Working knowledge of an additional language/ecosystem such as Java, .NET, Groovy, or Node.js. Strong problem-solving, communication, and collaboration skills. Key Responsibilities Design, build, and maintain AWS-based developer and DevOps platforms. Develop automation, infrastructure tooling, APIs, and production scripts using Python. Build and manage scalable CI/CD pipelines and release automation. Deploy and operate containerized applications using Docker and Kubernetes/EKS/ECS. Implement secure AWS IAM, authentication, and access-control patterns. Develop and integrate AI/LLM-based agents and tools into enterprise developer platforms. Apply LLMOps practices for agent evaluation, observability, reliability, and tool management. Implement Infrastructure as Code and reusable cloud deployment patterns. Promote DevSecOps, security-by-design, secure defaults, and operational simplicity. Create reusable platform patterns and solutions that can be adopted across multiple teams. Troubleshoot complex cloud, automation, identity, and platform issues. Coach and support engineering teams through reusable code, pipelines, automation, and platform solutions. Work effectively in ambiguous environments and turn experimental solutions into reliable production capabilities.

What you’ll do

Design and maintain AWS-based developer platforms and scalable CI/CD pipelines. Develop and integrate AI/LLM-based agents and tools into enterprise developer environments using Python.

Requirements

Requires 3-5+ years of experience in DevOps or platform engineering with strong Python and AWS production environment skills. Must have practical experience with containerization, Infrastructure as Code, and building AI/LLM-based tools.

Listed skills

• Kubernetes · Preferred
• CI/CD · Preferred
• Docker · Preferred
• Amazon Web Services · Preferred
• Terraform · Preferred
• Git · Preferred
• Python · Preferred

Other relevant skills

Identified from the job description. Confirm important requirements above.

• AWS
• Python
• CI/CD
• Kubernetes
• Docker
• Infrastructure as Code
• DevSecOps
• AI/LLM Tools
• LLMOps
• Terraform
• AWS IAM
• EKS
• ECS
• Git
• Cloud-native Platforms
• API Development

Job areas

• Software
• Technology
• Engineering
• Data & Analytics

More jobs from PeoplePilot