Lead AI Engineer

RBC•Toronto, ON

12d•Onsite

About The Position

Lead the development of enterprise-scale autonomous AI agents that transform RBC's Site Reliability Engineering operations. You'll architect and build intelligent agents using LangChain, LangGraph, and Claude that autonomously diagnose, resolve, and optimize production systems. This "lead-by-doing" role combines 70% hands-on engineering with 30% leadership, with full accountability from concept to production. Mentor 2-3 engineers, shape GAIA's agentic roadmap, and establish reusable frameworks that drive business impact across RBC. Every architectural decision is backed by working code. Work on cutting-edge agentic AI solutions that enable self-healing systems and drive innovation in autonomous operations at enterprise scale.

Requirements

Bachelor's degree in Computer Science, Software Engineering, Data Science, or related quantitative field
5+ years professional software engineering experience with 2-3+ years focused on Gen AI, AI agents, and autonomous systems development
Deep expertise with LangChain and LangGraph frameworks; proven experience with production-grade agentic systems (CrewAI, AutoGen)
Python mastery (FastAPI, Pydantic, async programming), backend API design (RESTful, GraphQL), and React/TypeScript for HITL interfaces
Proven track record delivering production-ready AI solutions with strong understanding of scalable architecture and distributed systems
Knowledge of LLM orchestration, tool use/function calling, multi-agent workflows, prompt engineering, and RAG architectures

Nice To Haves

Proficiency in Azure, AWS, or GCP within regulated/enterprise environments and experience with Infrastructure as Code (Terraform, Ansible)
Understanding of SRE principles, frameworks, observability, incident management, and reliability engineering practices
Knowledge of monitoring concepts (logs, metrics, traces, telemetry) and observability tools (Dynatrace, Elastic Stack, Prometheus, Grafana)
Hands-on DevOps experience and familiarity with production operations challenges including incident response and disaster recovery

Responsibilities

Code, architect, build, deploy, and maintain enterprise-scale agentic AI solutions with full accountability for scalable architecture and SLA maintenance
Build and ship autonomous agents that diagnose, resolve, and optimize production systems including self-healing infrastructure and dynamic disaster recovery
Design multi-agent stateful workflows using LangChain, LangGraph, Claude Agentic Skills, and Model Context Protocol (MCP) with human-in-the-loop patterns
Contribute to GAIA's Agentic Use Case Roadmap, prioritizing initiatives by business impact, technical feasibility, and ROI
Demonstrate reusable frameworks through working code and share knowledge via Knowledge Sessions and Engineering Council presentations
Provide technical guidance through pair programming and code reviews, mentoring 2-3 engineers on hands-on engineering excellence
Implement automated incident resolution, compliance monitoring, and security remediation capabilities for production operations
Ensure every architectural decision is backed by working code with zero delegation-only work