Lead Data Scientist

Stack

Responsibilities

• ▹Deliver production ML models in fraud, trust & safety, KYB, and compliance domains with measurable impact on customer workflows
• ▹Tackle classification problems with extreme class imbalance, sparse signals, and cold-start label challenges
• ▹Use graph-based techniques, weak supervision, LLMs, and AI agents to improve feature engineering and automate labeling
• ▹Partner with the ML infra team to design feature services, model training pipelines, model serving standards, and orchestration
• ▹Design and implement knowledge graph solutions, leveraging LLMs for graph construction, querying, and retrieval to enhance entity resolution

Requirements

• ▹7+ years of production ML experience in risk, fraud, credit, or trust & safety, with a track record of shipping external-facing ML applications
• ▹Hands-on experience building, querying, or extracting signals from knowledge graphs, ideally over business entity networks
• ▹Entity resolution experience across noisy, incomplete, or conflicting data sources in KYB, KYC, or AML contexts
• ▹Expertise in real-world ML challenges: imbalanced labels, sparse signals, cold start, and production version management
• ▹Hands-on ML infrastructure experience: feature stores, model management, training/serving pipelines
• ▹Comfort as a senior IC: setting technical direction, mentoring peers, and establishing best practices

Nice to have

• ▹B2B SaaS experience, ideally building ML products for enterprise customers
• ▹ML pipeline and automation engineering experience, building end-to-end training harnesses
• ▹Experience scaling ML across multiple products or risk domains

Soft skills

About the company

Since 2018, Middesk has been transforming business identity verification, replacing slow, manual processes with seamless access to complete, up-to-date data. It came out of Y Combinator, is backed by Sequoia Capital and Accel Partners, and was named to the Forbes Fintech 50 List.