Platform Architect (Cloud & Agentic Systems) - Contract

Audi RED

18h•Hybrid

About The Position

Audi Red is a groundbreaking partnership between Audi, the leader in premium automotive innovation and BIMM Management Group— a digital technology agency. As Audi’s flagship technology hub in North America, and aspiring to global recognition, Audi Red is dedicated to spearheading advancements in Audi’s digital experience ecosystem. Our mission is to merge excellence in innovation, design, and delivery, leveraging our strong partnership foundation to bridge agency creativity with product excellence, thus enhancing customer experience and service design through cutting-edge technological solutions. The Role We are seeking a Platform Architect on contract until December 24th, 2026 to help design and evolve Audi RED’s internal cloud platform, DevOps practices, and agentic (AI-driven) toolchain. This role focuses on building scalable, secure, and observable systems on AWS, while enabling engineering teams to leverage modern infrastructure and AI capabilities effectively. This role is highly hands-on and focused on platform development, system design, and internal enablement, rather than client delivery. This role focuses on building systems and platforms around existing AI/LLM capabilities, rather than developing or training models. We are open to remote candidates across Canada. You will be required to work EST hours. Candidates local to Toronto will be prioritized and asked to join us in office! This is an existing vacancy, not a made-up role — this one’s already got a desk waiting. Core Focus Areas Cloud Platform (AWS) DevOps & Infrastructure Automation Security & Governance Observability Agentic Systems & Toolchain (LLMs, MCP, workflows)

Requirements

Strong experience designing cloud-native systems on AWS
Experience with CI/CD and DevOps tooling
Experience with Infrastructure as Code
Strong understanding of cloud security (IAM, networking, secrets management)
Experience operating distributed systems in production
Experience with containerization and orchestration (Docker, Kubernetes/EKS)
Familiarity with agentic workflows and orchestration patterns
Understanding of Model Context Protocol (MCP)
Experience with RAG or search-based systems
Ability to design fault-tolerant systems

Nice To Haves

AWS certifications
Experience building internal developer platforms
Familiarity with vector databases or retrieval systems
Experience with LLM observability tooling
Experience with SRE practices
Exposure to policy-as-code or security automation tools
Experience optimizing LLM usage (cost, latency, caching)

Responsibilities

Design and evolve cloud-native platform architecture on AWS
Define and implement DevOps standards, including CI/CD, release strategies, and automation
Lead adoption of Infrastructure as Code (Terraform, CDK, CloudFormation)
Establish observability and APM standards (Datadog, OpenTelemetry, etc.)
Design and enforce secure-by-default architectures (IAM, networking, secrets management)
Drive reliability and scalability across distributed systems
Design and build the internal agentic platform
Implement Model Context Protocol (MCP) or similar patterns
Design agent orchestration patterns (multi-step workflows, tool calling)
Implement RAG systems using internal data sources
Establish best practices for prompt design and evaluation
Build guardrails and safety mechanisms for AI systems
Integrate agent workflows into internal services and APIs
Establish end-to-end observability across platform and agent systems
Optimize performance and cost across AWS and LLM usage