Lead Data Scientist at Middesk | San Francisco, United States | Rezi

Lead Data Scientist at Middesk

Lead Data Scientist

Middesk · San Francisco, United States

2 months ago

Lead Data Scientist

Middesk · San Francisco, United States

2 months ago
Resume preview

Impress employers and recruiters.
Choose from hundreds of resume examples.

Target Resume Now

About the Role

Actively building AI-driven applications to streamline customer workflows, focusing on business onboarding. Leveraging proprietary identity data and domain expertise, the company is expanding into AI-powered solutions for long-term growth. Seeking a hands-on applied ML expert to build the technical foundation, ideally with experience shipping external-facing models in risk/fraud, understanding challenges like imbalanced data and changing behavior. This highly technical role influences ML design, build, and scale at Middesk.

Responsibilities

  • Deliver production ML models for fraud, trust & safety, KYB, and compliance, impacting customer workflows.
  • Address complex classification problems involving extreme class imbalance, sparse signals, and cold start label challenges.
  • Innovate feature engineering and labeling using graph-based techniques, weak supervision, LLMs, and AI agents.
  • Partner with the ML infra team to design feature services, model training pipelines, serving standards, and orchestration for ML use cases.
  • Design and implement knowledge graph solutions using LLMs for construction, querying, and retrieval to enhance entity resolution and business identity.

Requirements

  • 5+ years of production ML experience.
  • Track record of shipping external-facing ML applications in risk, fraud, credit, or trust & safety.
  • Hands-on experience building, querying, or extracting signals from knowledge graphs, ideally over business entity networks for identity verification, fraud detection, or risk decisioning.
  • Experience with entity resolution for business or individual identities, linking records across noisy, incomplete, or conflicting data sources in KYB, KYC, AML, or identity verification.
  • Expertise in classification with real-world ML challenges: imbalanced labels, sparse signals, cold start, and production version management.
  • Hands-on ML infrastructure experience including feature stores, model management, and ML training/serving pipelines.
  • Ability to set technical direction, mentor peers, and establish best practices as a senior Individual Contributor.
  • B2B SaaS experience, ideally building ML products for enterprise customers.
  • Experience building end-to-end training harnesses for ML pipeline and automation engineering.
  • Experience scaling ML across multiple products or risk domains.

Skills

  • Applied ML
  • Production ML
  • Risk/Fraud ML
  • Classification
  • Graph-based techniques
  • Weak supervision
  • LLMs
  • AI agents
  • Feature engineering
  • Labeling
  • ML infrastructure
  • Feature services
  • Model training pipeline
  • Model serving standards
  • Orchestration
  • Knowledge graph solutions
  • Entity resolution
  • KYB
  • KYC
  • AML
  • Identity verification
  • Data validation
  • Model management

Location

  • SF/NYC office
  • within a commutable distance

Work Type

  • hybrid work model
  • 2 days per week in office

Experience Level

  • 5+ years of production ML experience
  • Senior Individual Contributor

About the Company

  • Middesk simplifies business collaboration through identity verification.
  • Since 2018, the company has transformed business identity verification, replacing manual processes with seamless access to complete, up-to-date data.
  • The platform helps companies verify business identities, onboard customers faster, and reduce risk.
  • Middesk is a Y Combinator alumnus, backed by Sequoia Capital and Accel Partners, and named to Forbes Fintech 50 List.