Senior Fraud AI Scientist - Consumer Risk Fraud

Location: New York

Job Summary
:
Intuit is the global financial technology platform that powers prosperity for the people and communities we serve. They are seeking a Senior AI Scientist to join their Consumer Risk Data Science team, focusing on developing innovative credit risk AI/ML fraud models to enhance money movement products.

Responsibilities
:

• 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 engineers

• 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.

Qualifications
:
Required
:

• Advanced Degree (Ph.D. / MS) in Computer Science, Data Science, AI, Mathematics, Statistics, Physics or a related quantitative discipline

• 3-6 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

Preferred
:

• Proficiency in deep learning ML frameworks such as Tensor Flow, PyTorch, etc.

• Work experience with public cloud platforms (especially GCP or AWS) and workflow orchestration tools like Apache Airflow

• Strong background in MLOps infrastructure and tooling, particularly Vertex AI or AWS Sage Maker, including pipelines, automated retraining, monitoring, and version control

• Experience with experimentation design and analysis, including A/B testing and statistical analysis.

Company
:
Intuit provides financial software solutions to empower individuals and businesses. Founded in 1983, the company is headquartered in Mountain View, USA, with a team of 10001+ employees. The company is currently Late Stage.