As an Applied AI/ML Scientist, you will design, build, and deploy advanced machine learning Models/ ML based Analytical Tools that drive the safety and reliability of our fraud prevention platform. Your work will have a measurable effect on the firm’s bottom line, with your models and recommendations directly contributing to loss savings and being regularly adopted by business stakeholders. You will operate at the intersection of research and production, taking full ownership of model performance from concept to deployment, and collaborate with scientists and engineers who thrive on innovation. This is a highly visible role, building scalable, reusable solutions that strengthen fraud prevention capabilities across the organization and influence the future of digital payments and financial security.

In this role, you will serve as a hands-on individual contributor while also mentoring junior team members as needed. You will help shape the technical direction of the team and build long-term, firmwide capabilities to identify and prevent fraud, leveraging cutting-edge techniques and modern cloud-based tools in an AWS environment.

Job Responsibilities:

Develop, train, and deploy machine learning models for fraud prevention and risk management. Research and implement novel architectures, including Graph Networks, Agentic AI, and Large Language Models. Build and test AI agents, iterating designs to enhance functionality and user experience. Conduct rigorous testing to ensure reliability and effectiveness of AI solutions. Use tools like Databricks and PySpark to create data pipelines and dashboards that support AI-driven insights and decision-making. Monitor and optimize model performance in real-world environments, adapting to evolving fraud patterns. Lead technical strategy and guide analytical direction within the team, fostering a culture of innovation and continuous improvement. Mentor and support junior team members, sharing best practices and technical expertise. Collaborate with cross-functional teams—including product, engineering, and data science—to align modeling solutions with business objectives and firmwide priorities. Contribute to the development of scalable, reusable machine learning solutions and best practices that strengthen the firm’s overall fraud prevention capabilities.

Required Qualifications, Capabilities, and Skills:

Master’s degree in Computer Science, Mathematics, Statistics, Economics, or a related quantitative field, or equivalent work experience. Minimal 10-year of experience in developing and managing predictive risk models in financial institutions. Deep understanding of machine learning theory and algorithms, with hands-on experience in both classical and deep learning methods. Proficient in Python, SQL or PySpark with experience in deep learning frameworks such as PyTorch or TensorFlow, and classical machine learning tools like XGBoost or Scikit-learn.  Knowledge of graph analytics including GSQL will be an added bonus.  Experience working with large datasets and building data pipelines using Databricks, PySpark, or similar technologies. Experience working in AWS cloud environments. Ability to build and test AI agents, iterate designs, and conduct rigorous testing for reliability and effectiveness. Experience mentoring or coaching junior team members.

Preferred/Additional Qualifications:

Experience or strong interest in Graph Analytics and Agentic AI. Knowledge of GSQL. Deep technical understanding of the mathematics behind algorithms, not just library usage. Product-first mindset, with a focus on the role models play in the user experience and overall product responsibility. Versatility in handling both tabular and non-tabular data using classical machine learning (e.g., trees/forests) and modern deep learning techniques. Driven by impact and energized by the responsibility of having your models make decisions on live financial transactions. Demonstrated ability to build scalable, reusable solutions that contribute to firmwide capabilities and long-term strategic goals.