AI Architect

TEEMA; Vaughan; On-site; CAD 80,000 - 100,000; Full time

Job summary

PureFacts is seeking an AI Engineer (LLM/Agent) to own the conversational layer for model outputs, build a Revenue Assistant agent, and design data-grounded context architecture. You will work at the intersection of ML, software, and product to create intelligent systems that automate workflows and augment decision-making.

Responsibilities include designing LLM-powered apps, building AI copilots, and integrating AI features into the PureRevenue platform while ensuring security, governance, and

Qualifications

• Experience building LLM-based applications and AI agents.
• Familiar with evaluation frameworks for generative AI and safety.
• Hands-on SaaS/fintech or data-driven environment experience.

Responsibilities

• Design and build LLM-powered apps and AI agents for internal and client use.
• Develop RAG pipelines and integration with data sources and tools.
• Create secure, scalable API services and microservices for AI features.
• Implement prompt engineering, tool usage, and agent orchestration.
• Evaluate outputs, monitor performance, and optimize models.
• Collaborate with Product, Engineering, and Client teams to deliver business value.

Skills

LLM development

Python

Agent frameworks

Prompt engineering

SQL

Education

Bachelor's in CS

Tools

OpenAI API

Azure OpenAI

LangChain

Weaviate

Job description

PureFacts is the leader in the Revenue Performance Management category for wealth and asset management firms. The PureRevenue™ Platform helps organizations maximize revenue potential by connecting pricing, billing, compensation, advisor behavior, and AI-powered intelligence within a single Revenue Book of Record. By transforming fragmented revenue processes into a coordinated growth system, firms gain greater visibility, stronger pricing discipline, improved revenue capture, and more effective advisor alignment. The result is faster organic growth, improved profitability, and increased enterprise value. For more than 25 years, PureFacts has helped leading financial institutions turn revenue from an operational process into a strategic advantage.

At PureFacts, we are building an AI-native platform and company. We embed AI, intelligent automation, and agentic workflows across our products and operations to detect anomalies, surface insights, streamline repetitive work, and support faster, better decision-making. In a highly regulated industry, we believe AI must be practical, governed, and auditable—amplifying human expertise while helping our teams and clients focus on higher-value, strategic work.

About the role

The AI Engineer (LLM/Agent) will own the conversational layer that describes Purefacts’ ML model outputs to end users, develop a “Revenue Assistant” Agent from R&D through to prototype, and design context architecture grounded in client‑specific pricing data. Builds evaluation and safety frameworks. This role sits at the intersection of machine learning, software engineering, and product, focusing on building intelligent systems that can reason, automate workflows, and augment human decision‑making.

What you'll do

LLM & Agent Development

Design and build LLM-powered applications and AI agents for both internal and client‑facing use cases. Develop solutions such as: AI copilots for internal teams and clients. Intelligent workflow automation agents. Natural language interfaces for data and reporting. Implement prompt engineering, tool usage, and agent orchestration frameworks.

AI-First Automation & Use Cases

Identify opportunities to replace manual processes with AI‑driven automation. Build systems that enable users to interact with complex data through natural language. Develop AI solutions that enhance: Revenue insights and analytics. Client reporting and communication. Operational efficiency across workflows.

System Design & Integration

Integrate LLMs into PureFacts’ SaaS platform and data systems. Build APIs and services to support AI‑powered features. Work with data and engineering teams to ensure secure, scalable, and reliable integrations.

Retrieval‑Augmented Generation (RAG) & Data Integration

Design and implement RAG pipelines using structured and unstructured data sources. Work with vector databases (e.g., Pinecone, Weaviate). Embedding models and semantic search. Ensure accurate, relevant, and context‑aware outputs from AI systems.

Evaluation, Testing & Optimization

Develop frameworks to evaluate LLM outputs for quality, accuracy, and reliability. Continuously optimize prompts, models, and workflows. Monitor system performance and implement improvements.

AI Infrastructure & Tooling

Leverage and integrate tools such as OpenAI, Azure OpenAI, or similar LLM providers. LangChain, LlamaIndex, or agent frameworks. APIs, microservices, and cloud infrastructure. Collaborate with MLOps to ensure scalable and maintainable deployments.

Responsible AI & Governance

Ensure AI solutions are secure, compliant, and aligned with responsible AI principles. Address data privacy and security. Model hallucination and reliability. Explainability and transparency.

Cross‑Functional Collaboration

Partner with Product, Engineering, and Client teams to translate AI capabilities into business value. Help stakeholders identify opportunities to increase efficiency and reduce manual effort. Communicate technical concepts in a clear, practical way.

Qualifications

Experience 1-3 years of LLM application development - RAG pipelines, vector databases, agent orchestration (tool‑use, multi‑step reasoning). Experience with evaluation frameworks for generative AI, and in putting guardrails/safety in regulated contexts. Familiar with agent frameworks (LangGraph or similar). Hands‑on experience building LLM‑based applications or AI agents. Experience in SaaS, fintech, or data‑driven environments is preferred.

Technical Skills

Strong programming skills in Python (required). Experience with LLM APIs (OpenAI, Azure OpenAI, Anthropic, etc.). Prompt engineering and agent frameworks (LangChain, LlamaIndex, etc.). APIs and microservices architecture. Data processing (SQL, Python data libraries). Familiarity with vector databases and embeddings. Cloud platforms (AWS, Azure, GCP).

AI & Agent Expertise

Experience building Retrieval‑Augmented Generation (RAG) systems. Multi‑step agent workflows. Tool‑using agents and automation systems. Strong understanding of LLM limitations and optimization techniques. Evaluation methods for generative AI.

Automation & Product Mindset

Passion for using AI to automate workflows and eliminate low‑value work. Ability to translate AI capabilities into practical, high‑impact solutions. Strong focus on user experience and real‑world application.

Ability to work across technical and non‑technical teams. Strong problem‑solving and systems thinking skills. Clear communication of complex AI concepts.

Education

Degree in Computer Science, Engineering, Data Science, or related field. Advanced degree is a plus but not required.

Key Success Metrics

Deployment of AI‑powered copilots and agents into production. Reduction in manual effort through AI‑driven automation. Adoption and usage of AI features by internal teams and clients. Quality, reliability, and accuracy of AI‑generated outputs. Speed of development and iteration of AI solutions.

Compensation

The pay range for this role is: 80,000 - 100,000 CAD per year (Toronto, Canada).