Data Scientist

At Middesk, we're building AI-driven applications that simplify customer workflows, starting with business onboarding. 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. The role includes building fraud and risk systems, working with messy real-world data, leveraging relationships in data, improving signal and labeling, and helping scale infrastructure. We follow a hybrid work model with an expectation of 2 days per week in our SF/NYC office.

Responsibilities

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

Requirements

5+ years of experience in fraud, risk, or trust & safety; Experience building and shipping production systems; Strong foundation in applied ML or data systems; Experience with graph or relational data approaches; Hands-on and pragmatic

Nice to have

Familiarity with knowledge graphs, network analysis, or entity linking