Production AI Infrastructure Engineer

Build production AI infrastructure in Canada using agent orchestration, retrieval-augmented generation, and evaluation frameworks. Focus on reliable, secure, scalable systems.

As an Applied AI Engineer, you will build and operate AI runtime infrastructure for production agent workflows. You will implement tool calling, RAG, grounding, and context retrieval systems. You will also develop evaluation harnesses, golden datasets, quality benchmarks, and safety controls. The work supports practical AI features for mission-critical customer workflows.

Key Responsibilities:

• Build and operate AI runtime and orchestration infrastructure
• Implement RAG, grounding, and context-retrieval systems
• Develop evaluation harnesses, datasets, and quality benchmarks
• Integrate testing, quality gates, and regression checks
• Own production reliability, latency, cost, and failure management

Requirements:

• Production experience shipping LLM- or ML-powered software
• Strong understanding of systematic AI evaluation methods
• Ability to manage cost and latency as constraints
• Clear communication with engineers, products, and customers
• Pragmatic judgment focused on measurable customer value

Apply applied AI engineering expertise across runtime architecture, RAG, evaluation, safety, and dependable production delivery.