Technology

We are looking for a Full Stack Engineer who can design and deliver scalable, enterprise-grade solutions while building AI capabilities directly into our platforms.
Has hands-on experience building with large language models and can apply them responsibly in a regulated setting

You will work across frontend, backend, and integration layers to build reliable systems, while delivering AI-enabled capabilities where they create genuine business value. Candidates are not expected to have a research background in machine learning. There will be opportunity to develop deeper expertise in areas such as agentic systems, orchestration, and model evaluation, supported by structured learning and meaningful project work.

Develop user-facing applications with a strong focus on usability and performance
Work on data-driven systems, integrations, and orchestration layers
Deliver AI-assisted capabilities including document processing, intelligent onboarding workflows, search and summarization, and decision support
Implement retrieval-augmented generation (RAG) capabilities that make internal policy, product, and client information accessible and actionable
Design, build, and support end-to-end applications across frontend, backend, and integration layers
Translate business requirements into scalable technical solutions
Build robust microservices and APIs using Java, Node.js, or Python
Develop intuitive frontend applications using React or Angular
Identify opportunities to leverage AI development tools to improve delivery efficiency
Contribute to continuous improvement of engineering practices covering quality, CI/CD, and observability
Develop features using LLM APIs, including prompt design, structured output handling, tool calling, and management of errors and edge cases
Implement and optimize RAG pipelines covering chunking strategy, embeddings, vector search, and grounding of responses in source documents




Establish validation and evaluation practices to assess AI output quality and identify regressions before release
Apply appropriate safety and security controls including input validation, PII handling, prompt injection mitigation, and human-in-the-loop review for material decisions
Manage cost and latency considerations associated with model usage

Core Technical Stack
Java (Spring Boot), Node.js, Python
Frontend: Angular or React
AI / LLM: LangChain, AWS Bedrock, Azure OpenAI, Copilot Studio, OpenAI and Anthropic APIs
Vector databases including pgvector, OpenSearch or Pinecone, or Chroma
Data: SQL/NoSQL, Oracle
Infrastructure: AWS/Azure, Docker, Kubernetes, Kafka
Tools: CI/CD pipelines, observability platforms
Candidates are not expected to have experience across the full stack listed. Proficiency in at least one backend language (Java, Node.js, or Python) and one frontend framework (React or Angular)
~ Strong understanding of system design, API development, and building for scale
~ Strong communication and collaboration skills, including the ability to engage non-technical stakeholders
~ Hands-on experience building applications with large language models, with the ability to discuss design decisions, challenges encountered, and lessons learned
~ Practical understanding of prompt engineering and methods for evaluating output quality
~ Familiarity with RAG concepts including embeddings, vector search, and the relationship between retrieval quality and output quality

Production experience supporting an LLM-based feature serving end users
Exposure to agentic AI,



including agents capable of planning and tool use, multi-agent workflows, and human-in-the-loop approval patterns
Experience with LangChain or LangGraph, AWS Bedrock, or Copilot Studio
Awareness of AI security considerations including prompt injection, data leakage, and output validation, with reference to the OWASP LLM Top 10
Familiarity with search, data retrieval, or analytics platforms
Experience using AI development tools such as Copilot and code assistants within a team setting

Applies considered judgement to AI, distinguishing between promising capability and production readiness
Risk-aware, recognizing that probabilistic outputs require appropriate controls in a banking context
Continuously learning, including how AI can enhance both products and engineering productivity
Salaries for part-time roles will be pro-rated based on number of hours regularly worked. BMO Financial Group’s total compensation package will vary based on the pay type of the position and may include performance-based incentives, discretionary bonuses, as well as other perks and rewards. BMO also offers health insurance, tuition reimbursement, accident and life insurance, and retirement savings plans. It calls on us to create lasting, positive change for our customers, our communities and our people. We strive to help you make an impact from day one – for yourself and our customers. We’ll support you with the tools and resources you need to reach new milestones, as you help our customers reach theirs. From in-depth training and coaching, to manager support and network-building opportunities, we’ll help you gain valuable experience, and broaden your skillset.

Accommodations are available on request for candidates taking part in all aspects of the selection process. A recruiting agency must first have a valid, written and fully executed agency agreement contract for service to submit resumes.

📌 Developer Lead (AI-Enabled Systems) (Ontario)
🏢 BMO Financial
📍 Ontario