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.

You will play a key role in advancing PureFacts’ AI‑first strategy, developing AI‑powered copilots, agents, and automation tools that reduce manual work, improve productivity, and deliver meaningful client value.

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
- 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:
- 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 transparent, practical way

Qualifications

- 2+ years building production, customer‑facing LLM/GenAI applications, including vector databases, RAG pipelines , agent orchestration
- 6‑8+ years of total back‑end software engineering experience
- Deep, hands‑on experience building with agent frameworks (e.g., Microsoft Agent Framework, Google ADK, LangGraph, etc.), including designing custom orchestration patterns beyond out‑of‑the‑box templates
- Demonstrated ownership of evaluation frameworks and pipelines and design of deterministic guardrails/safety controls in regulated or compliance‑sensitive contexts
- Experience in SaaS, fintech, or other data‑driven, regulated environments strongly preferred

Technical Skills

- Expert‑level Python (required)
- Deep experience with:
- LLM APIs (OpenAI, Azure OpenAI, Anthropic, etc.), including cost/latency tradeoffs at scale
- API and microservices architecture, including integrating LLM and ML model components into larger systems
- Data processing (SQL, Python data libraries) and pipeline design for both retrieval‑quality data and model training data
- Solid working knowledge of:
- Vector databases and embedding strategies (selection, tuning, hybrid search)
- Cloud platforms (AWS, Azure), including deployment and scaling of AI/ML workloads
- Proven experience architecting and shipping:
- Retrieval‑Augmented Generation (RAG) systems at production scale
- Multi‑step agent workflows wi

📌 Mechanical design engineer (Vaughan)
🏢 Rex Power Magnetics
📍 Vaughan