Staff Machine Learning Engineer, Underwriting and Credit

Block Block · Fintech · CA · Remote · 11003 Risk - Prod Dev - Square

Staff Machine Learning Engineer at Block, focusing on building and evolving ML systems for credit products like Cash App Borrow and Afterpay. The role involves the full modeling lifecycle, from problem formulation to production deployment and iteration, with a strong emphasis on agentic engineering workflows and AI tooling to accelerate development and ensure rigor. The position requires extensive experience in decisioning contexts and a deep understanding of borrower behavior and credit risk.

What you'd actually do

  1. Build, evaluate, and maintain underwriting and decisioning models across Cash App Borrow and Afterpay.
  2. Design and evolve credit decision frameworks, including the modeling, automation, and policy logic that manage credit exposure over time.
  3. Design and run experiments to evaluate model performance, measure impact on approval rates and loss, and inform credit policy decisions.
  4. Develop deep understanding of borrower behavior, repayment dynamics, and portfolio structure across both products, and use that to inform model design and decision logic.
  5. Contribute analysis and perspective that inform portfolio-level decisions, including explaining model behavior, tradeoffs, and uncertainty to senior technical and business leaders.

Skills

Required

  • Bachelor's degree in a quantitative field
  • 10+ years applying AI, machine learning, or statistical modeling in decisioning contexts
  • Experience with probabilistic models and decision systems
  • Strong experimentation skills
  • Experience with model monitoring, degradation detection, and retraining strategies
  • Proficiency with AI-native development workflows
  • Experience explaining modeling concepts, results, and limitations to senior stakeholders
  • Experience working across disciplines in environments with meaningful constraints

Nice to have

  • Advanced degrees welcome

What the JD emphasized

  • 10+ years applying AI, machine learning, or statistical modeling in decisioning contexts such as credit, risk, fraud, recommendations, or similar domains.
  • Proficiency with AI-native development workflows. You use LLMs, agentic coding tools, and AI-assisted automation as a regular part of how you build and ship.

Other signals

  • underwriting and decisioning models
  • credit decision frameworks
  • borrower behavior
  • agentic engineering workflows
  • AI developer tooling