AI Architect Toronto Canada

Role: AI Architect

Location: Toronto Canada (100% Onsite) –

FTE and C2C

Skills Required:

AI & ML

• Agentic AI
• RAG / Graph RAG
• LLMs, Vision-LLMs, Diffusion Models
• Inference optimization (vLLM, TGI)

Systems & Architecture

• Multi-agent orchestration
• Tool calling & safe action schemas
• Secure API integration
• End‑to‑end AI application design

Data & Platform

• Databricks ML, Unity Catalog, MLflow
• Vector Search & retrieval systems
• Document ingestion & OCR technologies

AI Safety & Governance

• Guardrail frameworks
• Evaluation tools
• Responsible AI compliance

Our Purpose

As we expand our AI capabilities, we seek an
AI Architect

to shape responsible, scalable, and innovative AI systems for Marketing Technology.

Overview

We are seeking an
AI Architect

to lead the design of next-generation enterprise AI systems centered on Agentic AI, advanced RAG patterns, multimodal model integration, and secure orchestration frameworks. This role focuses entirely on
model integration, inference optimization, safety, orchestration, document ingestion, evaluation, and architecture

. The architect will drive standards for multi-agent orchestration, tool calling, governance, and design patterns across business and engineering teams.

AI Strategy, Architecture & Governance

The AI Architect will define enterprise AI architecture that incorporates Agentic RAG, Graph RAG, Master-Agent orchestration, A2A agent communication, and MCP-based extensibility with tool calling. This involves shaping standards for how agents plan, reason, ground their responses, call tools safely, and collaborate autonomously. The role establishes architectural guardrails for tool schemas, action validation, lineage tracking, and auditability. It also sets direction for LLMOps and AgentOps patterns, ensuring alignment with data governance, responsible AI frameworks, and enterprise security requirements.

AI Solution Architecture

This role leads the end-to-end architecture of AI applications such as intelligent copilots, autonomous agents, workflow orchestration systems, knowledge-grounded assistants, and agentic marketing solutions. The architect integrates open-source and commercial LLMs, Vision-LLMs (e.g., Florence‑2, LLaVA, Qwen-VL), and diffusion models for text‑to‑image and emerging text‑to‑video capabilities. Rather than training models, the architect ensures secure, optimized inference and efficient orchestration using frameworks like vLLM, TGI, Hugging Face pipelines, and Databricks-first pipelines for governance (Unity Catalog), lineage tracking (MLflow), and semantic retrieval (Databricks Vector Search). Tool calling plays a central role as the architectural pattern for enabling LLMs and agents to safely interact with enterprise systems, APIs, knowledge stores, and other agents.

Knowledge Base Ingestion (PPT/PDF) Pipeline Architecture

The architect designs standardized, scalable ingestion workflows for enterprise PPT/PDF content using tools such as , MarkItDown, Apache Tika, PyMuPDF, and python‑pptx. These pipelines incorporate OCR and layout understanding through LayoutParser, docTR, PaddleOCR, and OpenCV, as well as Vision-LLMs for interpreting charts, diagrams, and complex layouts. Ingestion workflows support semantic chunking, metadata enrichment, table extraction, media handling, and slide-aware structuring, all governed through Unity Catalog with indexing and retrieval powered by Databricks Vector Search. Tool calling is incorporated to allow agents to retrieve, interpret, or update knowledge assets securely and dynamically.

AI Safety, Guardrails & Evaluation

The AI Architect leads the design of safety, grounding, and evaluation systems using frameworks like DeepTeam and NVIDIA NeMo Guardrails to enforce policy constraints, reduce hallucinations, ensure topic control, and maintain safe conversational boundaries. Evaluation strategies include DeepEval for behavioral and correctness testing, Ragas for RAG performance metrics, and human‑in‑the‑loop validation for high-stakes workflows. The role ensures every agent and LLM-powered system adheres to Responsible AI, data protection, and compliance frameworks, with robust logging, lineage, and auditability.

Technical Leadership

The AI Architect provides thought leadership across engineering, data, and product teams, creating reference architectures for AgentOps, RAG frameworks, tool calling patterns, ingestion pipelines, and evaluation standards. They guide architectural reviews, mentor teams on best practices for prompt design, grounding, safety, and workflow orchestration, and communicate complex AI strategies to both technical and executive stakeholders. The role requires strong judgment, clear articulation of trade-offs, and the ability to influence across multiple domains without direct authority.

All About You

You bring deep experience designing AI systems built on Agentic RAG, Graph RAG, multi-agent orchestration, and structured tool calling. You are skilled in integrating LLMs, Vision-LLMs, and diffusion models for inference and multimodal understanding, and you're comfortable architecting secure, compliant pipelines using platforms like Databricks ML, Unity Catalog, MLflow, and Databricks Vector Search. You have hands-on expertise with document ingestion frameworks for PPT/PDF content, OCR and layout tools, semantic chunking, and multimodal enrichment. You excel at bridging business, engineering, and governance perspectives, and you are committed to Responsible AI and secure enterprise design.

Corporate Security Responsibilities

All AI systems must comply with security, privacy, and model governance standards. This includes safeguarding sensitive data, following security policies, reporting incidents promptly, and completing required compliance and AI safety training.