AI & Full Stack Developer

University of Toronto • Toronto, ON

3d • CA$103,367 - CA$132,188 • Onsite

About The Position

The University of Toronto Libraries (UTL) system is the largest academic library in Canada and is ranked in the top five among peer institutions in North America. The system comprises 40 libraries located across three university campuses: St. George, Mississauga, and Scarborough. This diverse and extensive network of college libraries, special collections, and specialized information centres plays a pivotal role in supporting the teaching, scholarly, and research needs of nearly 100,000 students enrolled in a wide array of graduate, professional, and undergraduate programs. The library system provides access to millions of resources in various formats, including electronic, print, audio-visual, data and geospatial materials. UTL also boasts impressive holdings of archival material and substantial digital collections, securely preserved in the libraries' data centre. The staff at UTL are integral to the academic and scholarly enterprise, working closely with faculty and students to support their teaching, learning, and research requirements. They are subject matter experts; they are skilled in research data management, collections, statistics, GIS, metadata, digital preservation, scholarly communications, copyright, teaching, knowledge synthesis, open access and much more. Our work is grounded in our commitment to support equity, diversity, and inclusion. UTL continuously evolves to meet the changing academic priorities and pressures at the University and within the broader landscape of higher education.

Reporting to the Director of Digital Library Applications, the AI and Full Stack Developer will join a collaborative, multifunctional team of technologists and librarians to support digital library services and initiatives within the University of Toronto Libraries’ Information Technology Services department (UTL ITS).

The position will accelerate responsible adoption of AI at UTL by:

Preparing library-licensed data for AI use and implementing a production-grade Retrieval-Augmented Generation (RAG) system
Designing and implementing Model Context Protocol (MCP) servers to integrate approved AI tools with priority library web services and data sources
Developing and evaluating locally hosted, open-source LLM services to meet privacy, cost, and data-governance constraints

In addition, this position will strengthen the Digital Library Applications team by:

Designing and implementing sustainable architecture that spans digital services
Increasing software development standardization through consistent frameworks, shared components, and best practices (e.g., code reviews, testing, documentation)
Coordinating work and mentoring junior developers

Requirements

• Bachelor's Degree (Computer Science) or acceptable combination of equivalent experience.
• Minimum five years or equivalent experience in a developer role.
• Demonstrated experience incorporating AI coding assistants (e.g. GitHub Copilot, Claude, Cursor) into a professional development workflow, including critical evaluation and correction of AI-generated output
• Experience with prompt and context engineering techniques for code generation, refactoring, and documentation tasks
• Experience with agentic development workflows, including human-led AI orchestration across planning, task generation, implementation, testing, code review, and documentation phases
• Interest in or experience with LLM orchestration frameworks (e.g. LangChain, LangGraph, LlamaIndex, Vercel AI SDK)
• Hands-on experience or demonstrable self-directed learning in Retrieval Augmented Generation (RAG) pipeline design, including document ingestion, chunking strategies, embedding models, and vector store integration
• Experience building or experimenting with Model Context Protocol (MCP) servers, including tool design, transport configuration, and access control considerations
• Familiarity with local LLM deployment (e.g. Ollama, LM Studio) and the trade-offs between local inference and hosted API services
• Understanding of AI system evaluation, including assessing retrieval quality, output reliability, and failure modes in non-deterministic systems
• Awareness of privacy, data residency, and licensing considerations when designing AI pipelines that process PII or proprietary/licensed content
• Strong interest in designing AI systems with auditability, access controls, and data minimization in mind
• Significant expertise and knowledge of modern front-end and back-end web development languages and frameworks such as JavaScript (Next.js/React/Node), PHP (Laravel/Symfony), and Python
• Significant experience with relational (e.g. MariaDB, MySQL) and non-relational databases (e.g. MongoDB)
• Demonstrated ability to write technical documentation and deliver presentations
• Adaptable
• Goal oriented
• Insightful
• Intuitive
• Self-directed
• Team player

Nice To Haves

• Excellent written and verbal communication skills, with the ability to collaborate and communicate with stakeholders at various levels of technical understanding
• Experience with Docker, Kubernetes, and containerization principles
• Experience with Drupal 10/11
• Experience with data visualization
• Experience with Unix-based environments

Responsibilities

• Analyzing, recommending, and designing highly complex software architecture
• Developing and updating architectural framework for highly complex and confidential university-wide applications
• Writing complex technical code
• Evaluating programming code to ensure it has validity, compatibility, and that it meets appropriate standards
• Commenting on programming code for the purposes of standardization and consistency
• Analyzing, recommending and designing technical solutions for highly complex IT problems
• Leading and planning IT projects

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level