Agentic AI Architect

About AI Labb

AI Labb is the Data & AI division of TheAppLabb, a technology innovation firm that has launched 750+ applications over the past 18 years for global brands including Suncor, Loblaw, Petro Canada, RBC, Porter Airlines, Chatters, David Yurman, Meridian, Empire Life, First Canadian Title, Gateway Casinos, and the Canadian Standards Association.

We bridge the gap between AI's promise and business reality, delivering pragmatic AI solutions that create measurable business outcomes rather than theoretical possibilities. Our approach is business-first: we start with client objectives and work backward to ensure every AI initiative delivers measurable ROI. We are looking for builders who share this philosophy.

Our work increasingly takes us beyond individual AI use cases into designing enterprise agentic frameworks — the orchestration, observation, and decision-modelling layers that unify our clients' existing AI platforms into coherent, governable, brand-safe systems. We are connected into the Canada AI Alliance and Global AI Leaders Alliance networks, giving us cross-industry visibility into how the most demanding AI organizations are building.

Role Summary

We are looking for a hands-on AI Architect who can code, architect, and deploy across AWS, GCP, and Azure. You must be able to take a concept from a whiteboard to a working Proof of Concept independently, and you must also be able to step up a level — designing the cross-platform agentic frameworks our enterprise clients need to scale AI safely.

This role combines deep multi-cloud architecture expertise with modern agentic AI patterns to build autonomous systems that solve real business problems. You will work directly with clients across retail, luxury, financial services, healthcare, and manufacturing, translating business challenges into working AI solutions. You will also play a key role in growing the AI Labb team by technically vetting and onboarding future engineers.

The role is hands-on at the PoC stage and architectural at the framework stage — you should be equally comfortable shipping production-grade Python and producing a reference architecture a client's CTO will build against for the next two years.

Core Responsibilities
Hands-On Agentic AI Development

You will build PoCs independently without relying on a dev team for the initial build. This means designing and coding AI agents using cloud-native services (AWS Bedrock, Azure AI Foundry, Google Vertex AI / Gemini Enterprise Agent Platform) and modern agentic frameworks (LangChain, LangGraph, CrewAI, Microsoft AutoGen, Semantic Kernel, Google ADK, AWS Strands, OpenAI Agents SDK). You will implement reasoning, planning, and memory modules; configure LLMs to interact with external APIs, databases, and enterprise software to execute real-world tasks. Our clients expect working demonstrations, not slide decks.

Multi-Cloud Architecture

You will design scalable infrastructure across all three major hyperscalers and recommend the right one for each client's situation:

• AWS: Bedrock, Bedrock AgentCore, Strands Agents, AgentCore Policy, Lambda, Fargate, API Gateway, EventBridge, Step Functions, SageMaker.
• GCP: Gemini Enterprise Agent Platform / Vertex AI Agent Builder, Agent Development Kit (ADK), Agent Engine, Agent Studio, BigQuery, Cloud Run, Vertex AI Pipelines.
• Azure: AI Foundry, Copilot Studio, Semantic Kernel, Azure OpenAI Service, Azure Functions, Container Apps, Logic Apps.

You will select and optimize foundation models across providers (Bedrock, Vertex Model Garden, Azure OpenAI) based on cost, latency, performance, and data residency requirements. All architectures must meet strict security, compliance, and cost-optimization standards.

Agentic Framework Design (Orchestration, Observation, Decision Modelling)

Beyond individual agents, you will architect the cross-platform frameworks that sit above clients' existing AI stacks:

• Orchestration: Design how agents communicate, hand off, and share memory across platforms. Decide when to use native platform orchestration versus a thin custom layer. Codify cross-platform invocation patterns using A2A, MCP, and emerging interoperability standards.
• Observation: Architect tracing, evaluation, hallucination monitoring, drift detection, and cost telemetry across multi-platform agent workflows. Recommend the right observability stack per client — Openlayer, LangSmith, Arize, Langfuse, Galileo, Maxim, Datadog LLM Observability, or hyperscaler-native options.
• Decision Modelling: Design the policy catalog, guardrail enforcement model, and "where does this capability get built" routing rubric. Codify these in policy-as-code (OPA, Cedar, NeMo Guardrails, Microsoft Agent Governance Toolkit) and in business-readable formats that client AI Committees can actually use.

Client Delivery & Solution Design

You will participate in AI Discovery engagements to identify high-value opportunities within client organizations. You will translate business requirements into technical architectures that align with our outcome-driven methodology. You will lead the technical track of discovery engagements — stakeholder interviews, capability audits, framework design workshops, and executive readouts — and translate the architecture into clear business value for CEOs, CMOs, and AI Committee members. You will work alongside our AI Strategy and Implementation teams to deliver end-to-end solutions.

Build-vs-Buy and Platform Strategy

You will lead build-vs-buy analysis for each layer per client, with clear pros/cons grounded in their existing stack and team skills. You will maintain AI Labb's point of view on the orchestration, observation, and governance tooling landscape, refreshed quarterly. You are the person clients look to for "given my situation, what should I actually choose?"

Governance, Security, and Brand Safety

You will embed policy-as-code, identity, permissioning, PII handling, prompt-injection defense, and audit/observability into every architecture from day one. You will translate regulatory frameworks (EU AI Act, NIST AI RMF, ISO 42001, AIDA, Quebec Law 25, HIPAA where relevant) into enforceable controls within the framework.

Team Building & Technical Leadership

You will lead technical interviewing, selection, and onboarding for new hires within the AI Labb workstream. You will define technical standards and coding guidelines for our growing AI/ML team. You will mentor engineers and junior architects. You will contribute to knowledge transfer initiatives — building client capabilities rather than dependencies — and may contribute thought leadership through Canada AI Alliance and Global AI Leaders Alliance forums.

Integration & Data Foundations

You will integrate AI services into existing enterprise workflows and data pipelines. You will work fluently across enterprise platforms our clients commonly bring — Salesforce Agentforce, Snowflake Cortex, Microsoft Copilot Studio, ServiceNow AI Agent Studio — and the data infrastructure underneath them (Snowflake, Databricks, Redshift, BigQuery).

Must-Have Qualifications

• Cloud Certification: Must hold at least one of: AWS Certified Solutions Architect (Associate or Professional), Google Cloud Professional Cloud Architect / Professional Machine Learning Engineer, or Microsoft Azure Solutions Architect Expert. Working knowledge of the other two clouds is required even if certifications are only on one.
• Hands-On Coding: Strong proficiency in Python. You must be comfortable writing production-grade code, not just managing configurations or reviewing pull requests. TypeScript or Go is a plus given ADK and Strands SDK support.
• Cloud Background: Strong foundation in traditional cloud architecture including networking, IAM, identity, serverless patterns, and infrastructure-as-code. We expect you to have built cloud infrastructure before moving into AI.
• AI Stack: Proven experience with at least one hyperscaler AI platform (Amazon Bedrock + AgentCore, Vertex AI Agent Builder + ADK, or Azure AI Foundry) and operational fluency across all three. Hands-on with vector databases such as Pinecone, OpenSearch, pgvector, or equivalent.
• Agentic Experience: Demonstrated ability to build agents that utilize tools and function calling, with memory, planning, and multi-step reasoning. We are not looking for people who have only built simple chatbots. You should be able to describe agent topologies, memory strategies, and failure modes from real systems you have designed.
• Framework Fluency: Deep, current fluency with at least two of: LangGraph, CrewAI, Microsoft AutoGen, Semantic Kernel, Google ADK, AWS Strands, OpenAI Agents SDK, LlamaIndex Agent Workflows.
• LLM Observability: Practical experience with tooling such as Openlayer, LangSmith, Arize, Langfuse, or Galileo. Able to explain what each does well and where it falls short.
• Governance Tooling: Familiarity with policy-as-code and AI governance tooling — OPA, Cedar, NeMo Guardrails, Guardrails AI, Credo AI, or equivalent.
• Interoperability Standards: Working knowledge of MCP (Model Context Protocol) and A2A (Agent2Agent) and how they fit into enterprise agent architectures.
• Consulting Mindset: Ability to communicate technical concepts to business stakeholders, sit with a client's CTO and sketch an architecture, then sit with their CEO and explain why it matters.

Nice-to-Have Qualifications

• Data Background: High-level understanding of Snowflake, Databricks, Redshift, BigQuery, Synapse, and modern lakehouse patterns — to understand data lineage and retrieval strategies. This helps when working with our Data Foundation services.
• DevOps: Experience with CI/CD pipelines and infrastructure-as-code using Terraform, CDK, or Pulumi.
• RAG Implementation: Experience building production RAG systems with enterprise document collections, including evaluation and ongoing quality monitoring.
• MLOps: Familiarity with MLflow, Kubeflow, Vertex AI Pipelines, Azure ML, or Weights & Biases for model lifecycle management.
• Regulated-Industry Experience: Prior work in financial services, healthcare, luxury retail, or government — environments where brand integrity, privacy, and compliance are first-class constraints.
• Consulting Pedigree: Prior experience at a Big 4, top-tier strategy firm, or specialist AI consultancy.
• Public Footprint: Published work, open-source contributions, GitHub repos, or speaking history in the agentic AI space.

What You Will Work On

AI Labb delivers solutions across several domains. Here are examples of the types of projects you would contribute to:

• Designing the cross-platform agentic framework — orchestration, observation, and decision modelling — for an enterprise client unifying Salesforce Agentforce, Snowflake Cortex, Sigma, and Enterprise ChatGPT into a single governable system.
• Building multi-agent systems that reduce manual decision-making by 30% and improve response times by 40%.
• Implementing AI-driven quality monitoring for manufacturing clients that reduces batch rejections by 25%.
• Developing hyper-personalization engines for retail and luxury clients that increase digital conversion rates by 20–27%.
• Creating data pipelines and AI infrastructure that enable new AI initiatives while reducing data preparation time by 60%.
• Architecting observability, evaluation, and governance frameworks that pass enterprise brand, legal, and privacy review.
• Building reference architectures and reusable IP that scale across multiple AI Labb engagements.

Why AI Labb

• Work with Enterprise Clients: Our roster includes major brands across luxury retail, manufacturing, retail, financial services, and healthcare — including David Yurman, Suncor, Loblaw, RBC, Porter Airlines, and others.
• Business-First Philosophy: We cut through AI hype to deliver real value. Every project starts with measurable objectives.
• Direct Leadership Access: You will work closely with our VP of AI Engineering, Principal AI Solutions Architect, Chief AI Strategy Officer, and the CEO.
• Growth Opportunity: As an early member of a scaling team, you will shape our technical direction and build the team around you.
• Partnership Ecosystem: Access to AWS, Azure, Google Cloud, Snowflake, Databricks, and leading AI/ML platforms.
• Frontier Exposure: Through Canada AI Alliance and Global AI Leaders Alliance, you'll have visibility into how the most demanding AI organizations are building — and a platform to contribute back.
• Knowledge Transfer as a Deliverable: Our clients explicitly hire us to build their internal capability, not their dependency on us. You'll teach as much as you build.

How to Apply

Send your resume along with one of the following: a link to a GitHub repo showing an agentic AI project you have built, a brief write-up describing a complex AI system you have architected, or a demo video of a PoC you have created.

We want to see evidence that you can build, not just design.