Wealth - Lead - GenAI Testing and Evaluation Framework - Vice President job opportunity at Citibank.

Technical Certificate

New York, United States Of America

New York....United States Of America

We are seeking an #innovative and #detail-oriented professional to lead the development and management of the Generative AI (GenAI) testing and evaluation framework. This role focuses on creating patterns, methodologies, and iterative structures to optimize the performance and effectiveness of GenAI models, with a particular emphasis on prompt engineering and evaluation. The ideal candidate will have a strong background in GenAI, a deep understanding of natural language processing, and a passion for refining AI solutions through rigorous testing and iteration. __ Framework Development: Design and implement a comprehensive testing and evaluation framework for GenAI model outputs. Develop standards and patterns for assessing the quality and "goodness" of prompts across diverse use cases. Create iterative processes for testing and refining prompts to optimize model outputs. __ Prompt Engineering and Evaluation: Establish criteria for evaluating prompt performance, including accuracy, completeness, relevance, coherence, and alignment with desired outcomes. Experiment with prompt structures to identify optimal configurations for various business applications. Develop and document best practices for prompt design and refinement. __ Collaboration and Integration: Work closely with tech partners, engineers, and product teams to ensure testing frameworks integrate seamlessly into the development lifecycle. Partner with stakeholders to understand business requirements and tailor testing methodologies to address specific needs. Provide actionable insights and recommendations to improve model performance based on evaluation results. __ Tooling and Automation: Identify and implement tools for automating the testing and evaluation process. Develop dashboards and reporting mechanisms to monitor prompt and model performance metrics. Stay updated on emerging tools and techniques in AI testing and integrate them into the framework. __ Continuous Improvement: Establish feedback loops to iteratively improve testing methodologies and evaluation standards. Establish process for ongoing monitoring of prompts, once productionalized. Monitor industry trends and advancements in Generative AI to ensure the framework remains cutting-edge. Advocate for a culture of experimentation and continuous learning within the organization.