Data Scientist

About the role

ABOUT MIDDESK:

Middesk makes it easier for businesses to work together. Since 2018, we’ve been transforming business identity verification, replacing slow, manual processes with seamless access to complete, up-to-date data. Our platform helps companies across industries confidently verify business identities, onboard customers faster, and reduce risk at every stage of the customer lifecycle.

Middesk came out of Y Combinator, is backed by Sequoia Capital and Accel Partners, and was recently named to Forbes Fintech 50 List.

ABOUT THE ROLE:

We’re building AI-driven applications that simplify customer workflows, starting with business onboarding. With our proprietary identity data and deep domain expertise, we’re in a strong position to expand into a broader set of intelligent, risk-aware products.

We’re looking for a hands-on engineer to help build the foundation for these systems. This role is less about inventing new ML algorithms and more about applying the right techniques to messy, real-world problems. You’ve worked in fraud, risk, or trust domains, and you understand how bad actors behave, how data breaks, and how to still ship reliable systems anyway.

This is a highly technical, hands-on role with broad influence over how we design, build, and scale data-driven systems at Middesk.

We follow a hybrid work model, and for this role, there is an expectation of 2 days per week in our SF/NYC office. Candidates should be based within a commutable distance, as we believe in the value of in-person collaboration and building strong team connections while also supporting flexibility where possible.

WHAT YOU’LL DO:

- Build fraud & risk systems
Design and ship production systems that detect and prevent fraud across KYB, trust & safety, and compliance workflows.

- Work with messy, real-world data
Tackle problems with extreme class imbalance, sparse signals, evolving adversarial behavior, and limited ground truth.

- Leverage relationships in data
Apply graph-based approaches and entity resolution techniques to uncover hidden connections and improve risk detection.

- Improve signal & labeling
Use a mix of heuristics, weak supervision, and modern AI tools (including LLMs where appropriate) to generate better features and labels.

- Help scale our infrastructure
Partner with engineering to build and evolve systems for feature generation, model training, and production deployment across multiple use cases.

WHAT WE’RE LOOKING FOR:

- 5+ years of experience in fraud, risk, or trust & safety
You’ve worked on real-world fraud or abuse problems and understand the domain deeply.

- Experience building and shipping production systems
You’ve deployed models or data-driven systems that power external-facing products.

- Strong foundation in applied ML or data systems
Comfortable working on classification problems with real-world constraints like imbalanced data, sparse signals, and changing patterns.

- Experience with graph or relational data approaches
Familiarity with knowledge graphs, network analysis, or entity linking is strongly preferred.

- Hands-on and pragmatic
You focus on impact over perfection and know how to balance speed, accuracy, and maintainability.