Head of Fraud & Risk Data Science

Head of Fraud & Risk Data Science

Salary: $220K - $270K Employment Type: Full-Time Location Type: Remote (US or Canada)

Who We Are

Sardine is a leader in fraud prevention and AML compliance. Our platform leverages device intelligence, behavior biometrics, machine learning, and AI to proactively stop fraud. We empower over 300 banks, retailers, and fintechs globally to combat identity fraud, payment fraud, account takeovers, and social engineering scams. We have secured $145M in funding from prominent investors including Andreessen Horowitz, Activant, Visa, Experian, FIS, and Google Ventures.

Our Culture

While we have hubs in the Bay Area, NYC, Austin, and Toronto, we operate with a remote-first philosophy, embracing a #WorkFromAnywhere approach. We prioritize hiring talented, self-motivated individuals who demonstrate extreme ownership and a high growth orientation. Our focus is on performance, not arbitrary work hours, allowing our team members the flexibility to balance personal commitments with professional responsibilities.

About the Role

As the Head of Fraud & Risk Data Science, you will lead the team responsible for transforming raw risk and payments data into real-time decisions that power our platform. You will spearhead critical proof-of-concept (POC) and proof-of-value (POV) projects for enterprise customers and financial institutions, often playing a crucial role in securing new partnerships.

This is a hands-on leadership position for an individual passionate about fraud prevention, capable of building solutions from first principles, and thriving in high-stakes environments. You will collaborate closely with Product, Engineering, and Go-To-Market (GTM) teams to reduce fraud, enhance conversion rates, and ensure customers recognize the value of Sardine from day one.

What You'll Do

• Lead POCs and POVs: Drive end-to-end proof-of-concept and proof-of-value projects with prospective customers to demonstrate fraud-loss reduction and ROI using Sardine’s risk engine.
• Build and Optimize Systems: Develop, optimize, and scale real-time decision systems that integrate ML models, features, and rules across billions of events.
• Team Leadership: Hire, coach, and mentor a team of fraud analysts and data scientists.
• Implement Experimentation: Deploy experimentation frameworks (A/B tests, bandit models) to safely validate new strategies.
• Cross-Functional Collaboration: Partner with Product, Engineering, and Commercial teams to embed insights into dashboards, APIs, and pricing strategies.
• Stakeholder Communication: Present findings and strategies clearly and compellingly to customers, executives, and external stakeholders.
• Roadmap Development: Drive strategic thinking for new signals, feature development, and feedback loops to enhance platform intelligence and speed.

What You'll Bring

• Experience: 7+ years in fraud analytics, data science, or machine learning.
• Leadership: 2+ years of experience leading technical teams that have successfully shipped real-time risk solutions within high-growth payments, financial, or fintech companies.
• Proven Results: Demonstrated success in reducing fraud losses and false positives for consumer and/or B2B products, processing millions of daily transactions or selling millions of products annually.
• Technical Skills:
  • Strong background in applied ML, anomaly detection, and experimentation design.
  • Advanced SQL skills.
  • Familiarity with modern data infrastructure (e.g., Kafka, Flink, feature stores, vector databases).
• Communication: Executive presence and strong storytelling ability, capable of communicating data insights to both technical and non-technical audiences.
• Project Ownership: Experience owning and delivering POC/POV workstreams with measurable customer outcomes.

Compensation & Benefits

• Base Pay Range: $250,000 - $270,000 USD / $310,000 - $375,000 CAD
• Equity: Significant equity with tremendous upside potential.
• Benefits: Attractive benefits package.

Note: The compensation offered will be determined by factors such as candidate location, qualifications, work history, and interview performance, and may vary from the stated range.