Location: Onsite- Toronto, ON

Job type: Full-Time/Permanent Hiring

As an

Agent & DevOps Platform Engineer , you will design, scale, and secure the foundational infrastructure that powers our next-generation developer platforms and autonomous

AI/LLM agent frameworks . This is a highly specialized role bridging the gap between advanced cloud-native

Platform Engineering

and cutting-edge

LLMOps . You will not just build standalone AI applications—you will build the highly automated, multi-account AWS environments, robust CI/CD pipelines, and secure IAM patterns that allow autonomous agents and developers to ship code reliably, securely, and at enterprise scale.

Key Responsibilities

Infrastructure as Code & Automation:

Architect, deploy, and manage highly reliable multi-account AWS environments using

Terraform, CloudFormation, or AWS CDK .

Agent & Tooling Orchestration:

Build, deploy, and scale enterprise developer platforms, integrating

agentic orchestration frameworks (e.g., LangChain, LlamaIndex)

and custom toolchains into production pipelines.

Bulletproof Identity & Access:

Implement advanced

AWS IAM architectures

under the principle of least privilege, designing secure cross-account access, service-to-service authentication, and Kubernetes service accounts.

Container Platform Engineering:

Package and orchestrate distributed container systems using

Docker

and enterprise container platforms ( Amazon EKS, ECS, or Kubernetes ), configuring robust networking, ingress, and workload security.

LLMOps & Platform Observability:

Build the guardrails for production AI workloads, implementing systems for

prompt management, tool execution, model evaluation, observability (CloudWatch), and cost-reliability metrics .

Scale CI/CD & DevSecOps:

Treat security as a core software design constraint. Author high-quality reusable pipeline patterns,



build automation workflows, and enable decentralized DevOps practices across multiple business units.

System Ownership & Culture:

Act as a technical mentor whose coaching is reflected in clean working code, robust pipelines, and reusable modules. Define and solve core platform bottlenecks in ambiguous environments.

Required Qualifications

Experience:

3–5+ years of hands-on platform engineering, cloud architecture, and CI/CD operations within complex enterprise environments.

Programming:

Solid proficiency in

Python

for infrastructure tooling, API integrations, agent services, and advanced production scripting.

Technical Ecosystems:

Working competence in at least one additional development ecosystem (e.g.,

Java, .NET, Node.js, or Groovy ).

Cloud Native & Containers:

Deep production experience with

AWS cloud-native deployments

and container orchestration via

Docker and Kubernetes / Amazon EKS / ECS .

AWS Security Mastery:

Comprehensive knowledge of complex

AWS IAM

structures, including roles, policies, trust relationships, and secure machine-to-machine authentication.

AI/LLMOps Engineering:

Direct experience building, deploying, or scaling

AI/LLM-based tools or agents

in or near production. Solid understanding of prompt management, tool usage, and agent testing.

Methodology:

Strong grasp of Git-based workflows, release management at scale, and an uncompromising DevSecOps approach to system design.

Nice-to-Have Skills

Hands-on usage of advanced AWS ecosystem tools:

ECR, Lambda, Bedrock, CloudWatch, S3, Secrets Manager, Systems Manager, and VPC networking .

Familiarity with Kubernetes internals:

Helm, service accounts, ingress controllers, and network policies .

Prior experience working with framework tools like

LangChain or LlamaIndex .

Experience driving agile delivery models using Scrum, Kanban, or SAFe across multiple teams.

#J-18808-Ljbffr

📌 DevOps Platform Engineer | AI & LLMOps Infrastructure (Toronto)
🏢 K&K Global Talent Solutions
📍 Toronto