AI Engineer

Position overview

Key responsibilities

• Develop, test, and deploy stateful, multi-step agentic workflows and tool-calling systems.
• Build secure APIs, connectors, and protocols linking AI agents with internal services, databases, and enterprise platforms.
• Create scalable retrieval pipelines using vector search and RAG over structured and unstructured data.
• Collaborate across data science, product, architecture, and business teams to take proofs of concept into production.
• Implement evaluation metrics, automated tests, and observability for performance, latency, cost, and reliability.

Critical qualifications

• Degree in Computer Science, Engineering, or a related field.
• Two to four years of software engineering or data science experience, including one to two years building with LLMs and agentic architectures.
• Proficiency in Python, clean code architecture, robust API design, and production enterprise integrations.
• Practical familiarity with tool/function calling, agent orchestration, and RAG over enterprise data.
• Experience with a major cloud platform and structured and unstructured databases.
• Keep current with foundation model capabilities, agent protocols, and developer tools.

Preferred qualifications

• Preferred: enterprise AI deployment experience, such as GCP, microservices, or enterprise SaaS integrations.
• Preferred: familiarity with MCP or agent evaluation frameworks.
• Preferred: exposure to LLMOps/MLOps, prompt evaluation, trace logging, CI/CD, and containerized deployments.
• Preferred: collaboration with data science teams to productionize analytical pipelines.
• Preferred: public GitHub portfolio or open-source work demonstrating agent or LLM experimentation.

Work arrangement

• Hybrid work arrangement; successful candidates must be based in Canada and report to a Bell office at least three days per week.
• The listed Ontario job locations are Toronto and Mississauga.

Employment details