Resume Score

Check how well your resume matches this job before you apply.

Sign in to check score

About the role

  • AI Architect designing and delivering intelligent AI applications for enterprise clients. Working with teams to develop scalable, production-grade solutions for complex challenges.

Responsibilities

  • Architect and develop production-grade agentic AI applications using modern agent frameworks and orchestration tools
  • Design and implement tool calling/function calling patterns that integrate LLMs with LOB APIs, databases, enterprise applications, and external services
  • Lead LLM application architecture decisions, including prompt engineering, context management, RAG pipelines, vectorization, embeddings, and model evaluation
  • Manage memory and state in complex agentic systems across multi-turn, multi-agent workflows
  • Build and maintain scalable cloud infrastructure on Azure, AWS, or GCP, applying CI/CD, logging, monitoring, error handling, and secure deployment best practices
  • Collaborate with full-stack teams to integrate AI capabilities into end-to-end solutions
  • Contribute to the ongoing evolution of AOT's AI practice, tooling, and standards

Requirements

  • Hands-on experience in architecting and developing production-grade agentic AI applications
  • Experience with any of the code-first agent frameworks and orchestration frameworks such as LangGraph, LangChain, Microsoft Agent Framework, Semantic Kernel, AutoGen, Google - ADK, or similar
  • Experience with Prompt and Context Engineering principles and strategies
  • Strong hands-on programming experience in Python or .NET Core or Java
  • Experience implementing tool calling/function calling with LLMs, which interacts with LOB APIs, databases, enterprise applications, and external tools
  • Strong understanding of memory and state management in agentic systems
  • Solid cloud architecture experience on Azure or AWS or GCP
  • Experience with production engineering practices such as CI/CD (Azure Devops or Github), logging, monitoring, testing, error handling, and secure deployment
  • Strong understanding of LLM application architecture, including prompts, context management, RAG, vectorization, embeddings, and evaluation
  • Experience with MCP, A2A, and tool/server integration patterns (Nice-to-Have)
  • Experience with Azure AI Foundry - Model Deployments, Foundry Projects, Governance (Nice-to-Have)
  • Previous full-stack development experience (e.g., React/Angular, Python/.NET/Node.js) (Nice-to-Have)
  • Experience with Docker, Kubernetes, serverless platforms, or cloud-native deployment patterns (Nice-to-Have)
  • Certifications in AI, ML, or cloud (Nice-to-Have)
  • Any open-source codebase contributions or references, e.g., Github or GitLab (Nice-to-Have)
  • Experience in the public sector, financial services, or healthcare (Nice-to-Have)
  • Any experience with data engineering using Databricks, Microsoft Fabric or Snowflake (Nice-to-Have)

Benefits

  • Flexible remote work environment with optional hybrid collaboration in Victoria, BC
  • Continuous learning and leadership development opportunities
  • Flexible schedules and generous paid time off
  • Competitive health, dental, and wellness benefits from Day 1
  • Employer-sponsored deferred profit-sharing plan
  • A collaborative, mission-driven culture where your work matters

Job title

Job type

Full Time

Experience level

Mid levelSenior

Salary

CA$120,000 - CA$140,000 per year

Degree requirement

No Education Requirement

Tech skills

AngularAWSAzureCloudDockerGoogle Cloud PlatformJavaJavaScriptKubernetesNode.jsPythonReact.NET

Location requirements

RemoteCanada

Report this job

Found something wrong with the page? Please let us know by submitting a report below.