The leading provider of digital identity verification and fraud solutions. Salesinfo@socure.com
Senior Data Scientist – Fraud Data Infrastructure, Automation
Location
District Of Columbia + 1 moreAll locations: District Of Columbia | New York
Posted
48 days ago
Salary
$170K - $200K / year
Seniority
Senior
Job Description
Senior Data Scientist – Fraud Data Infrastructure, Automation
Socure
• Design, build, and maintain scalable data pipelines and workflows to support analytics, fraud detection, model development, and ongoing data monitoring (e.g., using Spark, Airflow, or similar distributed systems). • Leverage and build agentic AI and LLM-powered systems to automate data exploration, anomaly detection, vendor evaluation, and investigative workflows, increasing the speed and depth of insight generation. • Build and optimize models using a variety of input data types, including tabular data, natural language, point clouds, and images, in support of fraud detection and identity verification use cases. • Own data quality and integrity for critical datasets, implementing monitoring, validation checks, and anomaly detection to ensure reliable input to models and downstream decision systems. • Take ownership of project outcomes from scoping through delivery, managing data quality, technical trade-offs, and timelines; proactively escalate risks and work cross-functionally to resolve challenges. • Evaluate and integrate third-party data vendors and external datasets, including designing experiments to assess data quality, coverage, lift, and long-term value for Socure’s models and products. • Collaborate closely with Product, Engineering, and Risk teams to define data requirements, shape roadmap priorities, and deliver insights that guide strategic decisions for fraud and identity products. • Conduct in-depth research to explore new data sources and develop novel algorithms and features that advance the state of the art in fraud detection, identity resolution, and risk scoring. • Lead the end-to-end ML/analytics lifecycle for assigned projects: problem definition, data exploration, feature engineering, modeling, evaluation, deployment handoff, and post-deployment monitoring where applicable. • Present findings, trade-offs, and recommendations to technical and executive stakeholders with clarity and influence, adapting communication for audiences ranging from engineers to non-technical business leaders. • Mentor and share knowledge with peers and junior data scientists, fostering a culture of experimentation, rapid iteration, and continuous learning aligned to Socure’s leadership competencies. • Stay current with advancements in AI, machine learning, and data infrastructure (including LLMs and agentic frameworks), and apply innovative techniques to real-world fraud and identity problems. • Model Socure’s embedded leadership competencies in day-to-day work: continuous learning, effective communication, accountability, team development, decision making, and managing change.
Job Requirements
- Master’s or PhD in Computer Science, Statistics, Applied Mathematics, Data Science, or a related quantitative field; or equivalent professional experience.
- 5+ years of experience in data science, machine learning, or closely related roles, ideally in a high-growth tech or fintech environment.
- Experience in fraud prevention, risk modeling, or identity verification, including working with noisy, adversarial, or high-risk data environments.
- Proven experience working with large, messy, real-world datasets to generate insights and drive measurable business impact (not limited to pure model development).
- Experience working with diverse data modalities, such as tabular data, text/language, point clouds, and images, and selecting appropriate modeling approaches for each.
- Strong proficiency in Python and SQL, with hands-on experience using major ML libraries/frameworks (e.g., PyTorch, TensorFlow, scikit-learn) for model development and evaluation.
- Deep understanding of machine learning algorithms, model evaluation techniques (e.g., AUC, lift, calibration, stability), and data pipeline development for both batch and near-real-time use cases.
- Experience building and maintaining data pipelines and workflows in distributed or large-scale environments (e.g., Spark, Airflow, Databricks, or similar technologies).
- Demonstrated ability to evaluate and work with third-party data vendors or external datasets, including designing tests for data quality, coverage, stability, and incremental lift over existing signals.
- Experience with LLMs and agentic AI frameworks/infrastructure (e.g., LangChain, LangGraph, Ray) is strongly preferred; ability to design or extend agentic workflows for analytics and data quality use cases is a plus.
- Demonstrated ability to proactively deliver complex outcomes, lead technical workstreams, mentor others, and influence cross-functional decisions without formal authority.
- Excellent written and verbal communication skills, with the ability to translate complex data problems and model behavior into actionable business insights for both technical and non-technical audiences.
- Commitment to continuous learning, professional integrity, and high standards of business ethics, consistent with Socure’s leadership expectations.
Benefits
- Offers Equity
- Offers Bonus
Related Guides
Related Categories
Related Job Pages
More Data Scientist Jobs
Data Scientist
SardineCombine risk, compliance, and payment protection to increase customer trust and loyalty - all from one powerful API.
• Champion a data-first approach across internal teams and client engagements, promoting clarity and impact • Build and deploy machine learning models to prevent fraud across diverse fintech use cases • Use data and models to support the development of risk mitigation strategies and interventions while preserving and improving the user experience • Work directly with clients to understand challenges and deliver high-impact, data-driven solutions • Evolve our risk metrics, the supporting datasets, and how we measure the causal impact of initiatives • Collaborate with engineering to scale models into production and optimize performance
• Principal technical expert for how Geisinger evaluates, monitors, and optimizes AI systems • Set technical direction for AI evaluation across a growing portfolio • Provide technical leadership to a team of data analysts • Partner with AI program teams to improve validation and monitoring methods • Design validation studies and monitoring plans for AI systems • Instrument production monitoring and define measurable metrics • Mentor analysts on methodology and technical rigor
• Leads and manages the entire lifecycle of data science projects • Collaborates with cross-functional teams • Ensures projects align with organizational goals • Leverages deep understanding of machine learning algorithms • Utilizes clustering, dimension reduction, and deep generative models • Applies rigorous validation techniques • Oversees the deployment of models into production environments • Translates complex technical findings into compelling narratives • Mentors and guides junior data scientists • Contributes to developing best practices
Role Description Corteva Agriscience is looking for an entry level Biostatistics scientist to work at the intersection of world class statistics, biotechnology, and seed product design. This position will reside within the Seed Product Development Biostatistics team. - Research, develop, and implement statistical methodology and computational algorithms for optimized experimental design, analysis, and interpretation of biotechnology efficacy trials (insect, herbicide, and disease traits). - Support biotechnology trait advancements and provide statistical expert support for data analysis and actionable insights for global regulatory submissions. - Recommend and consult on state-of-the-art field and trial experimental designs and associated statistical analyses for optimizing agronomic performance data collection. - Contribute to resistance management strategies to support global regulatory submissions. - Collaborate with biotechnology trait characterization and development scientists on experimental design and statistical inference questions. - Provide statistical consultation and training to the seed and biotechnology product design community. - Work independently and as part of larger expert teams to provide focused statistical expert advice. - Participation in external collaborations and scientific publications is encouraged. Qualifications - PhD in Statistics, Biostatistics, or Mathematics. - Strong interest in experimental design and statistical theory. - Strong oral and written communication skills. - Solid foundation in applied statistical science with experience in mixed linear model methodology. - Demonstrated statistical computing programming skills; expert knowledge of SAS, R, Python, or related languages. - Ability to manage and manipulate large data sets. - Knowledge of basic principles of plant breeding, traditional and precision phenotyping, plant physiology, and gene editing is a plus. - Interest in learning about and operating in a commercial seed business setting. Requirements - Ability to convert statistical methodology into software systems using modern AI. - Proficiency in using large language models for statistical applications. - Ability and interest to contribute towards the development, testing, and deployment of internal scientific software and AI agents. Benefits - Numerous development opportunities offered to build your skills. - Health benefits for you and your family on your first day of employment. - Four weeks of paid time off and two weeks of well-being pay per year, plus paid holidays. - Excellent parental leave, including a minimum of 16 weeks for mother and father. - Competitive retirement savings plan and tuition reimbursement program.
