AI Engineer

Summary

The Team

The Applied AI & Data Science team builds and deploys production-grade AI solutions across Bell. We bridge the gap between cutting-edge AI research and operational enterprise systems, delivering autonomous agentic workflows, conversational intelligence, and machine learning systems that transform our internal operations and customer experiences.

Position Description

We are looking for a hands-on AI Engineer (CP2) to design, build, and deploy the next generation of AI-driven workflows and autonomous systems at Bell.

In this role, you will work closely with data scientists, senior engineers, and business squads to turn prototypes into reliable, production-ready AI applications. You will focus on building agentic workflows, integrating tools and enterprise services via modern protocols (such as Model Context Protocol), and connecting foundation models to enterprise data sources. The ideal candidate combines a strong software engineering foundation with a practical, builder mindset in the rapidly evolving LLM and agent ecosystem.

Key Responsibilities

• Build & Ship Agentic Applications: Develop, test, and deploy stateful, multi-step agentic workflows and tool-calling systems that automate complex operational and analytical processes.
• Enterprise System Integration: Implement robust APIs, connectors, and protocols (such as Model Context Protocol / MCP) to securely connect AI agents to internal services, databases, and enterprise platforms.
• Data & Knowledge Grounding: Build and maintain scalable data retrieval pipelines over structured and unstructured data, utilizing vector search and retrieval-augmented (RAG) architectures to ensure model accuracy and contextual awareness.
• Squad Collaboration: Partner with cross-functional squads (data scientists, product managers, and enterprise architects) to take solutions from rapid proof-of-concept to production deployments.
• Reliability & Quality: Implement evaluation metrics, automated unit/integration tests, and observability to monitor model performance, latency, cost, and reliability in production.

Critical Qualifications

• A degree in Computer Science, Engineering, or a related field.

• 2 to 4 years of professional software engineering or data science experience, including at least 1 to 2 years of hands-on experience building with LLMs and agentic architectures.
• Strong software engineering foundation: Proven proficiency in Python, clean code architecture, robust API design, and integration with production enterprise systems.
• Hands-on experience with modern AI patterns: Practical familiarity with tool/function calling, agent orchestration patterns, and retrieval-augmented generation (RAG) over enterprise data.
• Cloud & Data Systems: Experience deploying and operating applications on a major cloud platform (e.g. Google Cloud Platform) and working with structured/unstructured databases.
• Continuous Learning: An active habit of staying current with fast-moving foundation model capabilities, agent protocols, and developer tooling.

Preferred Qualifications

• Experience deploying AI applications within enterprise environments (e.g. GCP, microservices architecture, enterprise SaaS integrations).
• Familiarity with emerging open standards in AI tooling (e.g. Model Context Protocol / MCP, agent evaluation frameworks).
• Practical exposure to LLMOps / MLOps practices, including prompt evaluation, trace logging, CI/CD, and containerized deployments.
• Experience collaborating with or working alongside data science teams to productionize analytical pipelines.
• A public GitHub portfolio or open-source contributions demonstrating hands-on experimentation with agents or LLMs.