AI Application Engineer
What is the opportunity?
Join RBC as a hands-on technical lead building production-grade GenAI and Agentic AI applications for Cyber, Risk, Regulatory, Control & Security domains. This is an individual contributor role with no direct reports. You'll build the backend services that power autonomous and semi-autonomous AI agents, and work closely with AI Engineers to turn Lang Chain/Lang Graph prototypes into production applications deployed on Open Shift through our CI/CD pipeline.
If you want to write Python backend code, ship to production, and work at the intersection of software engineering and agentic AI in a regulated environment, this role is for you.
Join RBC as a hands-on technical lead building production-grade GenAI and Agentic AI applications for Cyber, Risk, Regulatory, Control & Security domains. This is an individual contributor role with no direct reports. You'll build the backend services that power autonomous and semi-autonomous AI agents, and work closely with AI Engineers to turn Lang Chain/Lang Graph prototypes into production applications deployed on Open Shift through our CI/CD pipeline.
If you want to write Python backend code, ship to production, and work at the intersection of software engineering and agentic AI in a regulated environment, this role is for you.
- Build and deploy backend services for Agentic AI applications using Python Django (preferred) or FastAPI, with Celery for async task processing and long-running agent workflows.
- Work with AI Engineers to product ionize their agents and proof-of-concepts, turning Lang Chain/Lang Graph prototypes into well-tested backend applications that run reliably in production.
- Deploy and operate applications on Open Shift Container Platform (OCP) and Kubernetes, using the Helios CI/CD pipeline to ship frequently.
- Build and maintain RESTful APIs that serve AI-powered applications, including authentication (OAuth2/JWT), rate limiting, input validation, and security controls appropriate for a regulated bank.
- Integrate AI capabilities into backend services: RAG pipelines, MCP (Model Context Protocol), A2A (Agent-to-Agent Protocol), multi-agent systems, and LLM-powered workflows. Profile and optimize AI application performance, including LLM token cost management, caching strategies, latency reduction, efficient agent orchestration, and production observability using Open Telemetry, Langfuse, or Lang Smith.
- Write unit and integration tests for backend services and agent workflows, and participate in code reviews to set the quality bar for the team.
- Mentor other engineers on backend and productionization best practices, collaborate with product owners, data scientists, and business stakeholders, and contribute to secure coding and AI safety guardrails for a regulated financial services environment.
Must-Have:
- 5+ years of software engineering experience with strong Python proficiency, including at least 2 years building backend services with Django, FastAPI, or a comparable framework.
- Hands-on experience with Celery or similar async task processing for managing long-running or distributed workloads.
- Strong understanding of API security, including authentication/authorization (OAuth2, JWT), rate limiting, input validation, and secure API design patterns.
- Experience deploying and operating containerized applications on Kubernetes or Open Shift, and working with CI/CD pipelines (Git Hub Actions, Jenkins, or equivalent).
- Familiarity with GenAI application patterns such as RAG, Agents, Agent orchestration, MCP, A2A, and multi-agent systems. Some hands-on experience with Lang Chain, Lang Graph, or similar frameworks is preferred.
- Experience with AI observability and traceability tools (Open Telemetry, Langfuse, or Lang Smith), and proficiency with agentic coding tools (Claude Code, Cursor, Windsurf, Devin, or similar).
- Experience with PostgreSQL, Redis, or vector databases (pgvector, FAISS, Milvus).
- Familiarity with Vue.js or React for occasional cross-stack work.
- Exposure to LLM providers (OpenAI, Anthropic Claude, Cohere, Llama), prompt/context engineering, and LLM cost optimization techniques such as token tracking, prompt compression, caching, and model routing.
- Familiarity with monitoring stacks (Grafana, Prometheus) and secure coding practices (SAST/DAST).
We thrive on the challenge to be our best, progressive thinking to keep growing, and working together to…
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).