Our transportation client is seeking a Senior AI Engineer (10+ years) to design, test, and optimize AI-driven quality monitoring solutions using Large Language Models, Snowflake, and Power BI Join a high-impact initiative focused on building AI-powered quality monitoring capabilities for Contact Centre operations within a consumer business workplace.

This role will design and optimize prompt engineering solutions, AI evaluation frameworks, and validation processes using Genesys transcript data, Snowflake, and Power BI.

The project focuses on scalable and data-driven assessments that improve evaluation coverage and operational insights for Quality Managers.

The resource will work closely with business and technology stakeholders to refine AI assessments through iterative testing and governance-aligned model evaluation.

Must Haves 10+ years delivering AI Engineering solutions using Large Language Models and custom prompt engineering Development of AI evaluation frameworks , benchmarking methodologies, test datasets, and validation processes Hands-on work with Python , SQL , and enterprise data platforms including Snowflake Work with unstructured conversational data including call transcripts, chat interactions,



or customer conversations Education related to AI Development or a comparable technical discipline Nice to Have Experience in Contact Centre, Customer Experience, Quality Assurance, or Speech Analytics environments Experience developing agent scoring, quality monitoring, sentiment analysis, or conversation intelligence solutions Experience with Power BI or comparable enterprise visualization tools Experience evaluating solutions across different languages, particularly English and French Experience with Retrieval-Augmented Generation architectures Responsibilities Design and optimize custom prompts that assess Contact Centre interactions against defined quality standards Translate business requirements and quality scorecards into structured AI evaluation criteria Develop test datasets, benchmarks, and validation methods to measure prompt accuracy, consistency, and reliability Compare prompting approaches and AI models to optimize quality, scalability, latency, and cost Validate AI-generated assessments against human Quality Manager evaluations Integrate AI-generated outputs with Snowflake-based data and analytics workflows Document prompt designs, evaluation results, governance requirements, and technical decisions

📌 Senior AI Engineer (10+ years) to design, test, and optimize AI-driven quality monitoring solutions using Large Language Models, Snowflake, and Power BI (Calgary)
🏢 S.i. Systems
📍 Calgary