Staff AI Engineer
About The Position
As a Staff Engineer on the ASEDA team, you'll be at the center of RBC's most ambitious AI bet — building the agentic AI and generative AI systems that are transforming how the enterprise operates. Think AI agents that can reason, plan, use tools, and take action across real business workflows — not chatbot demos, but production systems that move the needle. You'll design and ship MCP servers, agent orchestration pipelines, and RAG systems that connect large language models to the enterprise. You'll work across teams, set technical direction, and build the reusable patterns that let others move faster. This is a role where your code ships, your architecture decisions stick, and your ideas shape how AI gets adopted at scale. We value positive attitude, willingness to learn, open communication, teamwork, and commitment to clean, secure and well-tested code.
Requirements
- 5-8 years building production software systems — you know what it takes to ship and operate reliable code at scale
- 1-3 years working hands-on with LLMs and generative AI in production (not just POCs)
- Solid experience with agentic AI patterns — tool use, agent orchestration, ReAct, multi-step reasoning, memory and context management
- Strong Python skills and a commitment to writing clean, maintainable, production-grade code
- Experience building RAG systems with vector databases, embeddings, and retrieval strategies
- Working knowledge of MCP or similar agent-tool integration frameworks
- Comfort with cloud platforms (AWS, Azure, or GCP), containers (Docker/Kubernetes), and CI/CD
- Proven ability to lead technically — driving cross-team decisions, reviewing architecture, mentoring engineers
- Clear communicator who can explain complex AI trade-offs to both technical and business audiences
- Understanding of security, data governance, and responsible AI practices
Nice To Haves
- Experience with agent frameworks (LangChain, LangGraph, LlamaIndex, Semantic Kernel, CrewAI)
- Hands-on with AI observability tooling (LangSmith, LangFuse, Weights & Biases)
- Familiarity with multi-agent protocols (A2A) and the broader MCP ecosystem
- Background in NLP, information retrieval, or knowledge graphs
- Experience with prompt/context engineering at scale — versioning, evaluation, and reproducibility
Responsibilities
- Build agentic AI systems end-to-end — design and implement agent orchestration, MCP servers, RAG pipelines, and multi-agent workflows that run reliably in production
- Set technical direction — make architecture decisions on how agents interact with tools, manage context, route between models, and recover from failures
- Ship production AI — write clean, well-tested Python code for systems that real users and business teams depend on every day
- Drive quality and safety — build evaluation frameworks, prompt versioning, guardrails, and observability so agent behavior stays reliable across model updates
- Enable other teams — create reusable components, run enablement sessions, and mentor engineers on agentic AI patterns and best practices
- Stay at the frontier — evaluate emerging models, frameworks, and protocols (MCP, A2A) and bring the best ideas back to the team
Benefits
- Competitive total rewards — compensation, performance bonuses, flexible benefits, and stock options where applicable
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
