Fullstack AI Engineer - GFT Halifax

RBC • Halifax, NS

2d • Onsite

About The Position

Are you a passionate, innovative, and results-driven AI engineer who excels at building intelligent applications that transform how enterprise teams work? If so, we invite you to join our team! Global Functions Technology (GFT), part of RBC's Technology and Operations division, collaborates across the company to deliver cutting-edge AI solutions for our Risk, Audit, and Finance clients. We foster a culture of innovation, encouraging bold ideas and challenging the status quo. At GFT, you'll have opportunities to develop your technical, business, and professional skills, connect with colleagues through networking events, and benefit from mentorship and leadership support. Our leaders are committed to celebrating achievements and sharing knowledge to drive collective progress.

Requirements

• 2–4 years of hands-on Python development experience, with strong proficiency in Django and Django REST Framework
• Demonstrated experience building and deploying LLM-integrated applications using APIs such as OpenAI, Anthropic Claude, or AWS Bedrock
• Solid understanding of prompt engineering, tool/function calling, structured output generation, and multi-turn conversational AI patterns
• Experience with agentic AI frameworks such as LlamaIndex or LangChain, including workflow orchestration and RAG pipelines
• Strong proficiency with PostgreSQL, including schema design, raw SQL, and managing complex relational data models
• Experience with asynchronous Python programming (`asyncio`, `sync_to_async`) and background task processing
• Familiarity with RESTful API design, including building and consuming APIs with proper error handling and versioning
• Experience containerizing and deploying applications using Docker and OpenShift or Kubernetes
• Knowledge of security protocols relevant to AI integrations: OAuth 2.0, API key management, and secrets handling best practices

Nice To Haves

• Experience with document processing libraries (python-docx, pdfplumber, PyPDF2) and unstructured data extraction
• Exposure to vector databases or semantic search for embedding-based retrieval
• Experience with ML model evaluation, confidence scoring, or output quality validation
• Experience with CI/CD pipelines (GitHub Actions, Jenkins) and DevSecOps practices
• Exposure to enterprise audit, risk, or finance domain workflows

Responsibilities

• Design, develop, and deploy production-grade AI agents and LLM-powered workflows using Python, Django, and Django REST Framework.
• Integrate and orchestrate large language models (e.g., Claude, GPT) via API gateways, including prompt engineering, structured output parsing, function/tool calling, and multi-step reasoning chains.
• Build robust agentic workflows using frameworks such as LlamaIndex or LangChain, including event-driven multi-step pipelines, retrieval-augmented generation (RAG), and autonomous task execution.
• Design and implement asynchronous background task systems for long-running AI workloads, including worker orchestration, task queuing, and progress tracking against PostgreSQL backends.
• Develop RESTful APIs to expose AI capabilities to frontend applications and downstream services.
• Integrate ML models and AI services into enterprise applications, including embedding models, similarity search, and document understanding pipelines.
• Build document processing pipelines to extract and transform unstructured data (DOCX, PDF, VTT, JSON) into structured inputs for LLM consumption.
• Design and manage PostgreSQL schemas supporting complex AI workflows, including versioned data, audit trails, and session state management.
• Deploy and manage AI applications on OpenShift Container Platform (OCP) using Docker, with a strong focus on reliability, scalability, and security.
• Implement enterprise security patterns including OAuth 2.0 token management, SSL certificate handling, and secure credential management for LLM API integrations.
• Apply prompt safety techniques and output validation strategies to ensure responsible and reliable AI behavior in production.

Benefits

• Impactful work: Build meaningful, high-impact AI products used by enterprise audit and risk teams
• Growth & mentorship: Leaders who support your development through coaching and expanding opportunities
• Lasting impact: Ability to make a real difference through state-of-the-art AI engineering
• Great team: Work in a dynamic, collaborative, progressive, and high-performing environment
• Work-life balance: Flexible work/life balance options
• Challenging problems: Opportunities to tackle genuinely hard technical problems at the frontier of enterprise AI
• Career progression: Opportunities to take on progressively greater accountabilities as the AI platform scales

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed