Agent & DevOps Platform Engineer
Full Time
Toronto, ON (Onsite)
Required Skillsets:
- 5+ years of hands-on CI/CD, cloud, and platform engineering experience in enterprise environments
- Strong proficiency in Python for automation, API integrations, infrastructure tooling, agent services, and production scripting
- Working experience with at least one additional language or ecosystem such as Java, .NET, Groovy, or Node.js
- Hands-on AWS experience designing or operating production workloads
- Practical knowledge of AWS IAM, including roles, policies, trust relationships, cross-account access, least privilege, and service-to-service authentication
- Production experience building and deploying containers with Docker and a container platform such as Kubernetes, Amazon ECS, or Amazon EKS
• Experience building or integrating AI/LLM-based tools or agents in production or near-production environments
• Strong understanding of LLMOps concepts: prompt management, tool use, agent architectures, evaluation, observability, and reliability
- Experience with Git-based workflows, build automation, and release pipelines at scale
- Hands-on experience with Infrastructure as Code, configuration management, and cloud-native deployments
- DevSecOps mindset - security is a design constraint, not a checklist item
Good to have skills
• Experience with AWS services such as EKS, ECS, ECR, Lambda, Bedrock, CloudWatch, S3, Secrets Manager, Systems Manager, and VPC
• Experience with Terraform, CloudFormation, or AWS CDK
- Experience designing multi-account AWS environments and implementing enterprise identity and access patterns
- Familiarity with Kubernetes operations, Helm, service accounts, ingress, networking, and workload security
- Experience integrating AI into developer platforms or enterprise tooling, rather than only building standalone applications
- Prior work on agentic orchestration frameworks such as LangChain, LlamaIndex, or custom toolchains
- Experience enabling DevOps practices across multiple teams or business units
- Agile delivery experience using Scrum, Kanban, or SAFe
Roles and Responsibilities
- You build things and share them - your coaching is your working code, your pipelines, your agents, and your reusable platform patterns
- You think in systems: you understand the downstream effects of cloud, identity, container, and automation decisions
- You're comfortable in ambiguity and can define the right problem before solving the wrong one
- You have strong opinions on automation, reliability, security, IAM, and operational simplicity - and can defend them with evidence
- You learn fast, experiment deliberately, and know when to stop experimenting and ship
- You understand that secure defaults, clear ownership, and good developer experience are essential to platform adoption
