DataVisor is the world's leading AI-powered Fraud and Risk Platform that delivers the best overall detection coverage in the industry. With an open SaaS platform that supports easy consolidation and enrichment of any data, DataVisor's fraud and anti-money laundering (AML) solutions scale infinitely and enable organizations to act on fast-evolving fraud and money laundering activities in real time. Its patented unsupervised machine learning technology, advanced device intelligence, powerful decision engine, and investigation tools work together to provide significant performance lift from day one. DataVisor's platform is architected to support multiple use cases across different business units flexibly, dramatically lowering total cost of ownership, compared to legacy point solutions. DataVisor is recognized as an industry leader and has been adopted by many Fortune 500 companies across the globe.
Our award-winning software platform is powered by a team of world-class experts in big data, machine learning, security, and scalable infrastructure. Our culture is open, positive, collaborative, and results-driven. Come join us!
Role Summary
We are seeking a hands-on Data Scientist to own the detection strategy behind our AI-powered Fraud and AML Solutions suite. You will design the logic that decides what gets flagged — typologies, segmentation, thresholds, and false-positive tradeoffs — across Real-Time Payments (RTP), ACH, Wire, Check, and Application/Onboarding. You will also solve the industry-wide "Cold Start" problem: designing detection that protects new clients from day one, before their historical data is available.
This is a strategy and analytics role, and it is also a hands-on solutions role. Alongside designing detection, you will configure the platform that runs it, stand up tenants, write the documentation clients and colleagues rely on, and answer questions from teams across the company. You will work in Python and SQL every day, but the core of the job is judgment about risk.
Responsibilities
- Design Pre-Built Detection Strategies: Build, back-test and tune the strategies powering our core solution modules — RTP, ACH, Wire, Check, and Application/Onboarding — balancing catch rate against customer friction.
- Translate Typologies into Detection: Turn fraud and money-laundering typologies — synthetic identity, account takeover, scams, mule networks, structuring, check kiting — into concrete, testable detection logic.
- Solve "Cold Start": Design generalized detection that delivers immediate value to new clients, protecting them against known threats before their historical data is available.
- Configure the Platform: Set up and tune what makes detection usable — case manager review queues, alert detail layouts, knowledge graph and investigation lists — and stand up tenants for internal and client demos.
- Write for Clients and Colleagues: Produce the technical documentation, integration notes and solution write-ups that clients and internal teams work from.
- Answer the Business: Handle incoming questions from GTM, Solution Engineering, Customer Support and Technical Account Management — research the answer, with or without data, and write it up.
- Partner Cross-Functionally: Work with Product, Strategy, Data Science, Delivery and Engineering to take detection strategies from concept to production.
Requirements
Qualifications
- Education: BS or MS in Statistics, Mathematics, Economics, Computer Science, Engineering, or a related quantitative discipline. A master's is preferred, not required.
- Experience: At least 1 year of full-time professional experience in fraud strategy, AML/financial crime, risk analytics, data science or a closely related field. Internships are not counted toward this minimum.
- Domain Knowledge: Working understanding of fraud or AML typologies and payment rails (FedNow, RTP, ACH, Wire).
- Technical Core: Proficiency in Python (Pandas, NumPy, Scikit-learn) and SQL. Both are assessed in our technical screen.
- Analytical Rigor: Solid foundation in performance evaluation and tradeoff analysis — precision/recall, AUC, KS, false-positive rates, alert volumes, catch rate.
- Comfort Without Data: Able to propose a defensible approach when historical data is not yet available — which, for new clients, is the normal starting point.
Preferred qualifications
- Experience owning fraud or AML strategy at a bank, credit union, fintech or platform.
- Familiarity with rules engines, case management systems or alert-tuning workflows.
- Experience working through AI tooling — using LLMs to accelerate research, analysis or documentation, and able to judge when the output is wrong.
- Exposure to unsupervised learning, anomaly detection or graph/link analysis — as a consumer of these methods, not necessarily a builder.
- Client-facing or consulting background.
- Previous experience in a high-growth SaaS or Fintech environment.
Benefits
- Salary ranges between USD 120,000 and 170,000.
- Total compensation includes base salary, performance bonuses, and equity options.
- Comprehensive medical, dental, and vision insurance coverage.
- 401(k) retirement savings plan available.
- Discretionary Time Off (DTO) plus paid holidays.
- Opportunities for research, development, and professional advancement.
- Regular team-building events in a collaborative and innovative work environment.