Staff AI Scientist, Credit Karma

• Advanced Degree (Ph.D. / MS) in Computer Science, Data Science, AI, Mathematics, Statistics, Physics or a related quantitative discipline
• 6+ years of work experience in AI Science / Machine Learning and related areas
• Authoritative knowledge of Python and SQL
• Relevant work experience in fintech fraud risk, with deep understanding of money movement products, banking, lending, and fraud detection data
• Relevant work experience in credit risk and/or financial fraud risk, with deep understanding of payment systems, money movement products, banking, and lending
• Experience with and deep understanding of developing, deploying, monitoring and maintaining a variety of machine learning techniques, including but not limited to, deep learning, tree-based models, reinforcement learning, clustering, time series, causal analysis, and natural language processing
• Deep understanding of fraud risk modeling concepts, including fraud score calibration, label bias correction, case disposition logic, and network or graph-based link analysis for identifying organized or collusive fraud patterns
• Ability to quickly develop a deep statistical understanding of large, complex datasets
• Expertise in designing and building efficient and reusable data pipelines and framework for machine learning models
• Strong business problem solving, communication and collaboration skills
• Ambitious, results oriented, hardworking, team player, innovator and creative thinker
• Proven experience defining and driving end-to-end modeling frameworks, methodologies, or best practices across multiple product teams or domains
• Demonstrated ability to evaluate and integrate emerging AI/ML technologies, contributing to the company’s external technical visibility and innovation agenda

Desirable

• As we expand our primary banking and lending products, Intuit Credit Karma is looking for an innovative, experienced, and hands-on Staff AI Scientist to join our Consumer Risk Data Science team
• In this role, you’ll develop cutting-edge credit risk AI/ML fraud models to enable existing and new money movement products
• Join a collaborative and inventive team of AI scientists and machine learning engineers where your work will have a direct impact on hundreds of thousands of customers
• Contribute to the fraud risk AI science initiatives for the new and evolving Money product offerings, including complete hands-on ownership of the model lifecycle, sharing ownership of success and key results at the program-level, and driving the data strategy across all involved teams
• Design, build, deploy, evaluate, defend, and monitor machine learning models to predict and detect fraud risk for our primary banking product (CK Money) and various short-term lending products (e.g., tax refund advances, FNPL, installment loans, single payment loans, and early wage access)
• Collaborate with credit policy, product and fraud risk teams to ensure models align with business goals and product offering to drive actionable lending decisions
• Build efficient and reusable data pipelines for feature generation, model development, scoring, and reporting using Python, SQL, and both commercially available and proprietary Machine Learning and AI infrastructures
• Deploy models in a production environment in collaboration with other AI scientists and machine learning enginers
• Ensure model fairness, interpretability, and compliance
• Contribute to the evolution of our data and machine learning infrastructure within the Intuit ecosystem to improve efficiency and effectiveness of AI science solutions
• Research and implement practical and creative machine learning and statistical approaches suitable for our fast-paced, growing environment
• Solve hard, meaningful problems giving customers (not fraudsters) access to their hard-earned money alongside fun, smart people
• Experience professional growth and encourage growth throughout the team
• Work cross functionally (with executives, engineering, policy & rules, product, analytics, operations and other AI science teams) to ensure efficient and effective use of data science in ways that make an immediate, substantial, and sustainable impact