At Jaris, we’re redefining how financial services are delivered by building the modern infrastructure that powers embedded finance for platforms, processors, ISOs, and banks. Our platform streamlines everything from merchant onboarding and underwriting to bank account provisioning, compliance, and money movement — enabling our partners to launch financial products quickly and scale them confidently. By delivering the full stack of enablement tools and value-added financial services, we help our partners unlock new revenue streams and deliver better experiences to their customers.

As we expand our impact, we're looking for curious, driven people who want to help modernize the financial ecosystem and support the small businesses that power the economy.

About The Role

: We are seeking an experienced Data Scientist to own the identity verification and fraud monitoring systems at the heart of Jaris's merchant onboarding and embedded finance products. You'll work within a modern Databricks-native ML stack building real-time detection systems, modeling identity and transaction data for a diverse set of Small and Medium-sized Businesses, and continually refining prevention strategies as fraud patterns evolve. You will have the opportunity to work on cutting-edge projects at the intersection of data science, economics, and finance in a collaborative and dynamic work environment with ample room for professional growth and development.

If you are passionate about leveraging data to drive impactful decisions and thrive in a fast-paced environment, we encourage you to apply for this exciting opportunity!

Responsibilities

: Identify emerging fraud patterns (application fraud, synthetic identity, chargeback fraud, merchant-level risk) from a diverse dataset of SMBs spanning multiple industries. Build predictive models and rules-based systems for fraud detection, identity verification, and BSA/AML compliance across Jaris' embedded financial products. Partner cross-functionally with Compliance, Risk Operations, and Engineering to translate risk policies into reliable, production-grade systems.

Integrate signals from first and third-party data sources (KYB/KYC providers, transaction history, behavioral features) into production feature pipelines. Develop metrics and monitoring to track model health and performance. Apply LLMs and generative AI techniques to entity enrichment, document analysis, and investigator tooling where appropriate.

Qualifications

: 2 - 4 years of experience in a data science or machine learning role, preferably with a focus on fraud detection, identity risk, or financial risk modeling. Bachelor's degree in a quantitative field, such as Statistics, Computer Science, Mathematics, Finance, or similar. Proficient in Python and SQL, including common data science frameworks such as scikit-learn, XGBoost/LightGBM, and PySpark.

Strong understanding of fraud-specific ML challenges such as class imbalance, adversarial adaptation, and precision-recall tradeoffs. Professional experience maintaining models in production, including drift detection and model alerting. Excellent communication skills with the ability to convey complex outcomes to non-technical stakeholders.

In-office in Burlingame, CA at least 3 days per week.

, and location.

Nice To Have

S. D) is highly preferred but not required given a suitable combination of education and experience.

Requirements

, or regulatory contexts relevant to lending and banking. Familiarity with streaming or event-driven data pipelines is a plus.

Compensation

in the range of $95,000 to $140,000 USD.

Benefits

include: Company equity 401(k) pla