About this role
The day-to-day work for this Senior Data Scientist involves driving innovation in credit scoring models and researching new applications of AI and Large Language Models (LLMs). This role centers on leveraging expertise in structured and unstructured data to generate unique insights that inform product development and new offerings within the fintech space. The individual will be deeply involved in the entire lifecycle of ML models, from research and development to deployment and continuous monitoring. A significant focus will be placed on exploring credit and open banking research initiatives, analyzing pilot programs with external partners, and ensuring that the resulting AI solutions are accurate, explainable, and support responsible lending practices.
This position exists to advance VantageScore's capabilities by embedding advanced AI/ML and GenAI techniques into core credit scoring functions. The scientist will act as a subject matter expert on LLMs, focusing on adapting and fine-tuning models while maintaining necessary compliance and explainability standards. They will collaborate closely with engineering teams to move models into scalable production systems, ensuring they handle high volumes of data effectively. This role is ideal for someone who enjoys tackling complex, ambiguous problems and translating deep technical analysis into clear, actionable business strategies for both technical and non-technical audiences.
Candidates who excel in this role possess a strong blend of quantitative rigor, practical machine learning experience, and forward-thinking knowledge of emerging AI technologies. Success in this position requires not only technical proficiency but also the ability to drive thought leadership through publications and presentations, championing innovation within the team.
What you will do
- Conduct advanced research on structured and unstructured data to develop insights that support product management and new product development.
- Contribute to the design, development, evaluation, and deployment of machine learning models, specifically focusing on credit risk and predictive models.
- Serve as the team’s expert on GenAI/LLMs, focusing on adapting and fine-tuning models to ensure explainability and compliance.
- Drive pilot program analyses, including back-testing, rejection inference, and performance assessments using varied datasets.
- Improve and maintain existing model monitoring processes and create visualizations to communicate key insights to stakeholders.
- Partner with engineers to operationalize models into production systems, ensuring scalability and resilience under high data volumes.
- Research and apply emerging AI/ML and GenAI/LLM technologies to stay current with state-of-the-art methods.
- Translate complex analyses into clear, actionable business recommendations for various audiences.
What you need
- A Master’s or PhD degree in a quantitative field such as Data Science, Applied Mathematics/Statistics, Computer Science, Engineering, or Econometrics is required.
- Candidates must possess 3 to 5 years of professional experience in advanced analytics, AI/ML/LLM, and data science within research or corporate settings.
- Proficiency in Python is necessary for executing data science and machine learning workflows.
- Proven experience with core machine learning techniques, including classification, clustering, regression, and neural networks, particularly for predictive risk and credit modeling.
- A strong track record of conducting thorough research, developing analyses, and producing clear and impactful presentations or publications.
- Demonstrated experience delivering insights and solutions that result in measurable business impact.
- Experience working effectively within Agile methodologies and cross-functional teams is essential.
Nice to have
- Deep expertise in GenAI - Natural Language Processing (NLP) and Large Language Models (LLMs) - including training, fine-tuning, explainability, and deployment.
- Deep expertise in advanced ML techniques (self-supervised learning, training optimization, explainability) with a focus on credit scoring.
- Proficiency with modern ML/AI technology stack, such as PyTorch and AWS and related tools.
- Experience delivering innovative, scalable AI/ML solutions integrated into production platforms.
- High-level analytical problem-solving ability with creativity in defining and solving ambiguous problems.
- Exceptional communication skills capable of conveying technical concepts to diverse stakeholders.
- Self-motivated with a collaborative mindset and leadership presence.
Benefits
- 401(K) matched up to 7%
- Flexible Time Off
- 12 Paid Holidays
- Medical/Dental/Vision/Wellness benefits
- Monthly Team Events
- Modern Work/Collaboration Spaces
Skills and tech stack
Questions candidates ask
What is the remote policy for this role?
The role is hybrid, with a preference for working in Washington D.C. or New York, NY.
What is the salary range for this position?
The salary range for this position is 120K-150K/year, plus a discretionary bonus.
What is the primary tech stack used?
The required technical stack includes proficiency in Python for data science and machine learning workflows, along with preferred expertise in PyTorch and AWS.
What does the team environment look like?
The role involves partnering cross-functionally with engineers and is situated within a team of analytics professionals and developers.
What is the growth potential?
The role involves contributing to thought leadership through white papers, presentations, and insights shared internally and externally.