*** Bilingualism (English and French) is mandatory. Interviews are conducted mostly in French ***

As an Applied AI Developer III within LGI's AI Lab, you will design and deploy artificial intelligence components integrated into LGI's healthcare solutions. As part of a small multidisciplinary team dedicated to applied AI, your work will focus on one or more of the following areas: AI application development and model integration, data architecture and RAG systems, and/or AI deployment and operations (LLMOps).

This is not a fundamental research position. You will explore and prototype solutions in an environment where selected approaches may ultimately be integrated into production products, subject to real-world requirements related to compliance, performance, and data sovereignty. The role is primarily focused on experimentation and demonstrating what is possible with today's AI technologies in response to the practical needs of healthcare professionals.

What You'll Do

AI Prototyping & Development

• Build prototypes, assess technical feasibility, and iterate rapidly to validate concrete AI use cases.
• Develop AI-powered features and services integrated into LGI products, including information extraction, clinical summarization, decision support, documentation generation, and more.
• Integrate LLMs and model APIs into existing product workflows while evaluating and optimizing cost, quality, and latency.
• Test and support the production deployment of AI applications developed within the AI Lab.

Data, Quality & RAG Architecture

• Design and implement RAG (Retrieval-Augmented Generation) pipelines for semantic search and contextual generation across structured and unstructured clinical and administrative data.
• Build and maintain data ingestion, indexing, and structuring pipelines while ensuring data quality, freshness, traceability, and governance, in compliance with Quebec's Law 25 and PIPEDA requirements.
• Develop NLP components for extraction, analysis, classification, and structured output of medical texts and healthcare data.

Deployment, Operations & LLMOps

• Build and maintain AI deployment pipelines, including CI/CD processes, model versioning, prompt management, and tooling.
• Monitor model quality, performance, and costs; identify reliability, security, and incident management requirements, including rollback and escalation strategies.
• Establish evaluation metrics for AI pipelines, including relevance, hallucination rates, latency, and model drift.
• Maintain thorough technical documentation of architectures, design decisions, and operational practices.

Collaboration & Knowledge Sharing

• Work closely with LGI's R&D, Product, and Architecture teams.
• Participate in AI technology monitoring and contribute to the definition of standards, best practices, and governance frameworks.

Types of Projects in the AI Lab

Depending on ongoing initiatives and your background, you will explore different approaches, build prototypes, and evaluate their potential before contributing to the incubation and integration of the most promising solutions.

Projects may include:

• Adding new capabilities to our products using LLMs, specialized or predictive models, AI services, and optimization algorithms.
• Leveraging structured and unstructured data to make information more accessible and actionable through ingestion, semantic search, and RAG-based approaches.
• Automating tasks and business processes, extracting and transforming information, and supporting decision-making.
• Experimenting with and comparing various models, architectures, and approaches to assess quality, reliability, latency, cost, and security implications.
• Evolving promising prototypes into robust, observable, and product-ready solutions that can be seamlessly integrated into LGI's offerings.