Remote Data Scientist - Credit Risk Analytics

Prosper; San Francisco, Phoenix (CA, AZ); Híbrido; USD 129.000 - 179.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Udemy access

Childcare assistance

Pet insurance

Beneplace

Descripción de la vacante

Prosper is seeking a Data Scientist in the Credit Risk Analytics vertical, combining hands-on ML model development with shaping credit risk strategy. You will deliver predictive models and collaborate with engineering to deploy them in production, leveraging diverse data sources to drive risk decisions.

The role emphasizes building scalable credit and fraud strategies, communicating insights to risk management and leadership, and advancing internal tooling to boost productivity and governance.

Formación

• 2-3+ years of work experience in fintech, finance, or another high-impact field applying statistical and machine learning predictive techniques.
• Advanced degree (M.S./Ph.D.) preferably in statistics, computer science, engineering, physical sciences, economics, or a related technical field.
• Expert knowledge of statistical programming languages (e.g., Python) and database languages (e.g., SQL).
• Solid understanding of coding best practices, model documentation, and ML ops principles.
• Strong communication skills with the ability to translate complex technical subject matter into clear, actionable business strategies for cross-functional partners and senior management.
• Strong ability to collaborate seamlessly with people across various functions (engineering, product, compliance) and build strong relationships.
• Ability to work unsupervised in a fast-paced environment, effectively prioritizing among parallel technical and strategic projects.
• Ability to innovate within regulatory guidelines with a strong commitment to reproducible research and model governance.
• Self-motivated, results-oriented, enthusiastic, and a creative thinker who bridges the gap between data science and business strategy.

Responsabilidades

• Build industry-leading machine learning models for managing credit and fraud risks. Collaborate closely with engineering to deploy models into a production environment.
• Leverage complex data sources (e.g., credit bureau reports, customer-supplied information) at scale to develop credit and fraud strategies to improve the credit performance and optimize risk decisions.
• Propose and execute strategic solutions to complex business problems, operating effectively within constraints and aligning with broader company objectives.
• Analyze ad-hoc portfolio performance at a granular segment level on an ongoing basis. Identify trends and conduct root-cause analysis to isolate key performance drivers. Communicate findings and recommendations to the Risk Management and broader Prosper community.
• Help the team develop internal tools and workflow solutions to increase data science productivity and operational efficiency.
• Actively monitor credit risk models and strategies in production, extracting actionable insights to significantly impact key business metrics.
• Assess the potential usefulness and validity of new machine learning algorithms and features sourced from diverse, alternative data providers.
• Conduct high-impact, ad-hoc analyses supporting risk management, investor services, operations, and corporate development initiatives.

Conocimientos

Machine learning

Python

ML Ops

Communication

Cross-functional collaboration

Educación

MS/PhD in statistics, CS, engineering, physical sciences, economics, or related field

Herramientas

Python

SQL

Descripción del empleo

Prosper is seeking a Data Scientist in the Credit Risk Analytics vertical, combining hands-on ML model development with shaping credit risk strategy. You will deliver predictive models and collaborate with engineering to deploy them in production, leveraging diverse data sources to drive risk decisions.

The role emphasizes building scalable credit and fraud strategies, communicating insights to risk management and leadership, and advancing internal tooling to boost productivity and governance.