Staff AI Engineer (Global Security)
Royal Bank of Canada View all jobs
- Toronto, ON
- Permanent
- Full-time
- Design, develop, and maintain sophisticated NLP and Generative AI applications in Python; architect scalable agentic AI systems, RAG pipelines, and LLM integrations leveraging vector databases, embeddings, and advanced prompt engineering
- Design and implement Model Context Protocol (MCP) servers for enterprise data integration; build custom MCP servers connecting LLM applications to internal databases, APIs, and knowledge bases; contribute to existing MCP deployments developing new features and optimizations
- Build and maintain deployment pipelines to cloud platforms (OpenShift, Azure, AWS); containerize applications using Docker; build CI/CD workflows with GitHub Actions; manage MCP server infrastructure with proper authentication, security, and monitoring
- Develop AI-driven security tools and applications for scalability and resiliency; integrate applications with SIEM systems for alerting and reporting
- Establish technical direction and architectural standards for MCP server development, AI framework selection, and prompt engineering practices across Global Security; lead architectural reviews of team implementations
- Lead the design of complex, multi-system AI integrations; architect for scalability, resilience, and cost optimization at enterprise scale
- Define AI strategy in collaboration with product leadership; translate business objectives into technical roadmaps, prioritization, and architectural decisions
- Perform root-cause analysis for production issues and provide solutions; manage risks, assumptions, and constraints; communicate to appropriate parties
- 5+ years software development experience with 2+ years in AI/ML; expert-level Python proficiency for production systems
- Deep expertise designing and deploying NLP/Generative AI applications; proven track record with vector databases, LLMs, and RAG pipelines
- Expert-level experience with Model Context Protocol (MCP) servers for enterprise data integration; proven track record implementing complex multi-system AI architectures
- 1-2+ years hands-on experience with Anthropic Claude API and SDK (function calling, tool use, extended context) OR equivalent production LLM experience
- Advanced proficiency with AI frameworks (FastAPI, LangChain, LangGraph) and Python libraries (NumPy, Pandas, scikit-learn)
- Advanced prompt engineering expertise: multi-step reasoning, prompt caching strategies, cost optimization, Anthropic Skills framework, and agent orchestration patterns
- Solid understanding of cloud platforms (OCP, Azure, AWS), web services (SOAP/REST), Git/GitHub Actions, Docker, databases (SQL/NoSQL), middleware (Kafka/Redis), and JSON-RPC protocols
- Demonstrated experience leading or architecting large-scale AI/ML projects from conception through production; ability to make high-impact design decisions with long-term implications
- MLOps tools, service mesh architectures, API gateway patterns, and cloud certifications (AWS/Azure)
- Familiarity with SIEM integration patterns and security incident management workflow
- Understanding of Docker and other containerization platforms
- A comprehensive Total Rewards Program including bonuses and flexible benefits, competitive compensation, commissions, and stock where applicable
- Leaders who support your development through coaching and managing opportunities
- Ability to make a difference and lasting impact
- Work in a dynamic, collaborative, progressive, and high-performing team
- Flexible work/life balance options
- Opportunities to do challenging work
- Opportunities to take on progressively greater accountabilities
- Access to a variety of job opportunities across business