Staff Data Scientist - Fraud & Risk
Staff Data Scientist designs and deploys advanced deep learning models for fraud detection and risk management, leading ML lifecycle and mentoring peers. Requires 8+ years experience, Master's/PhD, and expertise in Python, PyTorch, and diverse data modalities.
About the job
Responsibilities
- Design, develop, and implement advanced deep learning models, including transformers, CNNs/RNNs, and graph learning algorithms, to address complex fraud and risk challenges.
- Build and optimize models using a variety of input data types, including tabular data, natural language, point clouds, and images.
- Lead the end-to-end machine learning lifecycle: data exploration, feature engineering, model training, evaluation, deployment, and monitoring in production environments.
- Take ownership of project outcomes, data quality, and delivery timelines; proactively escalate issues and work collaboratively to resolve challenges.
- Mentor and share knowledge with peers and junior data scientists, fostering a culture of experimentation, rapid iteration, and continuous learning.
- Collaborate cross-functionally with Product, Engineering, and Risk teams to define data requirements and drive insights that guide strategic decisions.
- Conduct in-depth research to explore new data sources and develop novel algorithms that advance the state of the art in fraud detection.
- Present findings and recommendations to technical and executive stakeholders with clarity and influence.
- Stay current with advancements in AI and machine learning, applying innovative approaches to real-world problems.
Requirements
- Master’s or PhD in Computer Science, Statistics, Applied Mathematics, Data Science, or a related field; or equivalent professional experience.
- 8+ years of experience in data science, machine learning, or related fields, ideally in a high-growth tech or fintech environment.
- Experience in fraud prevention, risk modeling, or identity verification.
- Hands-on experience developing and deploying deep learning models (such as transformers, CNNs/RNNs, and graph learning).
- Experience working with diverse data modalities, such as tabular data, text/language, point clouds, and images.
- Strong proficiency in Python, SQL, and major ML libraries/frameworks (e.g., PyTorch, TensorFlow, scikit-learn).
- Deep understanding of machine learning algorithms, model evaluation techniques, and data pipeline development.
- Experience with model deployment and monitoring in production environments (real-time model inferencing is a plus).
Nice-to-Haves
- Experience with LLMs and Agentic AI framework/infrastructure (e.g., LangChain, LangGraph, Ray).
Skills
Python, SQL, PyTorch, TensorFlow, scikit-learn, Deep Learning, Transformers, Cnns, Rnns, Graph Learning, LLMs, LangChain
Similar jobs
Data Science jobs
United States
Leads end-to-end quantitative research and user-centered metric development for Pinterest’s consumer experience, partnering closely with Data Science and Engineering. The role requires 7+ years of experience, expertise in survey methodology, experimentation, statistical modeling, and model evaluation, plus strong cross-functional and leadership communication skills.
Shield AI
Washington, DC
Leads operational analysis, modeling, simulation, and wargaming for autonomous aircraft systems, translating military mission insights into design and product decisions. Requires 7+ years of experience, defense operational expertise, and proficiency with aerospace simulation tools and modern software workflows.
Suno
New York, NY
Leads data science for growth and monetization, shaping pricing, packaging, conversion, retention, and new revenue models. Requires 6–8+ years in data science or product analytics, advanced SQL and Python, rigorous experimentation experience, and strong cross-functional influence.
Suno
San Francisco, CA
The first dedicated Trust & Safety data scientist will define ecosystem metrics, run experiments, evaluate safety models, and shape the roadmap with Product, Engineering, and Legal. Requires 6–8 years of data science experience, Trust & Safety or adjacent domain expertise, and strong SQL and Python skills.
Komodo Health
United States
Leads client-facing healthcare research engagements using real-world data, advanced statistical methods, and AI-enabled workflows. Requires an advanced quantitative degree, at least five years of healthcare research or analytics experience, strong client advisory skills, and expertise in RWE/HEOR studies.