AI Engineer

Accountabilities: • Build full-stack features and components for AI pilots and prototypes, including backend services, REST APIs, data connectors, and frontend implementations.

• Develop clean, well-documented code designed for reliable handoff to teams responsible for maintaining operational systems. • Integrate AI applications with cloud platforms, data infrastructure, internal APIs, API gateways, and data sources such as Snowflake. • Follow established API gateway, data access, schema, and integration standards while collaborating with internal platform teams. • Contribute to an internal AI agent library by implementing reusable agent patterns, writing tests, instrumenting traces, and documenting module behavior. • Build and maintain AI agent capabilities, including tool integrations, API connectors, evaluation harnesses, and observability instrumentation. • Develop baseline evaluations that help verify AI agent behavior, reliability, and consistency before systems are relied upon. • Work with frontier model APIs, agentic frameworks such as LangGraph and CrewAI, and MCP server integrations. • Collaborate closely with AI and product experience engineers to implement frontend components, connect user interfaces with backend services, and contribute to shared component libraries. • Support technical scoping for new initiatives by identifying integration dependencies, investigating technical unknowns, and estimating implementation effort. • Participate in emerging technology evaluations by building proof-of-concept implementations and contributing findings to technology assessments. • Apply observability and testing practices throughout development so AI systems are traceable, inspectable, and maintainable. • Contribute to an AI engineering environment where successful prototypes can evolve into reusable, production-oriented capabilities.

Requirements:

• Strong full-stack software engineering fundamentals, including backend development, REST APIs, cloud-native service patterns, data integrations, and frontend implementation. • Demonstrated experience building something real with an LLM or AI system, such as an AI agent, RAG pipeline, tool-calling integration, or comparable application. • Genuine curiosity about AI systems and a strong interest in following developments in frontier models, agentic architectures, and AI-assisted software development. • Practical understanding of RAG, tool calling, LLM APIs, and modern AI application patterns. • Strong ability to write clean, maintainable, well-documented code and learn quickly in a technically demanding environment. • Ability to absorb technical direction, ask thoughtful questions, work through ambiguity, and contribute without requiring fully defined specifications. • Experience with Python and/or TypeScript is highly valuable. • Familiarity with LangChain, LangGraph, CrewAI , or comparable agent frameworks is an asset. • Experience with Snowflake, BigQuery , or another cloud-based data platform is beneficial. • Understanding of RAG architectures, vector databases such as pgvector, Pinecone, or Weaviate , and basic AI evaluation harnesses is preferred. • Familiarity with AI observability concepts, including traces and logs, and tools such as Langfuse or LangSmith , is an advantage. • Strong collaboration and communication skills, with the ability to work effectively alongside principal-level engineers and cross-functional technical partners. • A proactive, fast-learning, delivery-oriented mindset and willingness to experiment with emerging AI technologies. • Candidates must be legally authorized to work in Canada, as employment sponsorship is not provided for this position.