AI QA Engineer

Arbitration Forums Inc.•Tampa, FL

22h•Remote

About The Position

This role at Arbitration Forums is as unique as it is rewarding because of the AF IPAAL Values (Integrity, Passion, Accountability, Achievement, Leadership) and TRI Model (Trust, Respect, Inclusion). The AI Quality Assurance Engineer is responsible for safeguarding the integrity of AI systems by meticulously overseeing the testing process to identify bugs and inconsistencies. This role serves as the last line of defense, ensuring that only the most reliable AI solutions are deployed. This role is responsible for designing, developing, and optimizing test cases for AI solutions, ensuring that models and prompts for generative AI are producing the expected outputs prior to full integration into business processes and applications. The incumbent will partner with stakeholders to drive business value to Arbitration Forums and our members through fully tested AI solutions for deployment through a myriad of implementation methods.

Requirements

Bachelor’s or Master’s degree in Computer Science, Information Systems, Data Science, Linguistics, or a related field.
Minimum of 7 years of experience in AI solution testing, software quality assurance, data governance, data science, or a related role.
Expertise in complex testing frameworks with combined AI and programmatic solutions, including multiple deployment methods.
Advanced programming knowledge, including mastery of programming languages such as Python and Java.
Deep understanding of machine learning and AI principles, from generative models to predictive advanced algorithms.
Cloud computing and knowledge for deploying and managing AI applications on cloud platforms like Microsoft Azure. Understanding of containerization technologies like Docker and orchestration tools like Kubernetes for scaling AI solutions.
Data management knowledge, including data pre-processing, augmentation, and generation of synthetic data, including the cleaning, labeling, and augmenting of data to train and improve AI models.
Strong understanding of natural language processing concepts and techniques.
Proficiency in programming languages such as Python, R, and familiarity with AI frameworks (e.g., TensorFlow, Selenium, PyTorch).
Working knowledge of testing frameworks, from techniques to automate web applications to validation of machine learning models, including Model Context Protocols and SHAP.
Experience with continuous integration and delivery in the context of DevOps and MLOps.
Working knowledge of cloud services (i.e., MS Azure, AWS, Google Cloud).
Experience with AI tools, such as MS Azure ML, Databricks AI, Snowflake CortexAI, Dataiku.
Strong knowledge of data governance, data security, and compliance practices.
Familiarity with data visualization and reporting tools (e.g., Webfocus, Power BI).
Excellent analytical and problem-solving abilities.
Strong communication and interpersonal skills to collaborate with cross-functional teams.
Ability to lead projects and mentor junior staff.

Nice To Haves

Auto Insurance claims industry experience preferred.

Responsibilities

Test Design, Creation, and Optimization:
Design, develop, and implement comprehensive test plans to ensure AI system functionality aligns with specifications.
Design automated test cases and monitor results to inform mitigation actions in case of degradation.
Conduct automated and manual tests to evaluate the AI system’s performance under different scenarios and deployment methods.
Collaborate with Data Scientist and GenAI Engineers to pinpoint issues and refine the AI system.
Document test results and feedback into the development cycle for continuous improvement.
Stay abreast of new testing tools and methodologies to enhance testing efficacy and cost effectiveness.
Ensuring the AI system adheres to regulatory standards and ethical considerations.
Collaborate with cross-functional teams to ensure that test cases are traceable to the original requirements.
Conduct and automate A/B testing of variants and diversions when needed, including deviations and degradations.
Collaborate with stakeholders to integrate tested AI solutions into business processes, products, or workflows.
Script test cases for automation and maintain a reusable library of test cases.
Partner with the AI Engineers, MLOps Engineer, and other stakeholders to establish and implement observability and monitoring frameworks to adequately and timely identify degradations and potential ethical/bias issues.
Work with AI engineers to establish and implement explainability frameworks to ensure ability to demonstrate how AI systems work, why they work that way, and how the data is used to produce specific outcomes.
Collaborate with stakeholders in the simulation of different user behaviors to measure end-to-end AI system resilience.
Provide recommendations for improvement in the areas of AI acceptable use and ethics, collaborating with Legal and Compliance to ensure adherence.
Define the requirements and processes, as well as own, the AI Quality Assurance environment for production-mirror testing of data and AI solutions.
AI Governance and Security:
Ensure the data continuum for testing purposes.
Ensure that data security protocols are tested in AI solutions in accordance with regulatory requirements and company policies.
Collaboration and Strategy:
Work closely with IT, product architecture, data engineers, data analysts, data scientists, and business stakeholders to understand needs, data requirements, and test AI solutions.
Provide technical leadership and mentorship to junior data team members.
Provide training and support to team members on effective AI testing strategies.
Lead AI systems and model observability efforts to ensure adherence to company policies and enforce governance standards.
Other duties as assigned by manager or project needs.