Staff Machine Learning Engineer, Radar

What you'll do

• Set the technical strategy and multi-quarter roadmap for lifecycle abuse machine learning.
• Design a persistent consumer risk profile combining signals from signups, logins, payments, and product usage.
• Lead the development of models for multi-accounting, account takeover, bots, and refund abuse using graph and LLM-based approaches.
• Design methods to learn from sparse, delayed, and merchant-specific labels using LLM-assisted labeling and network signals.
• Define success metrics, evaluation frameworks, and ROI estimates to help businesses balance abuse losses against growth.
• Write production code and personally build the most technically difficult components of the abuse prevention layer.
• Build AI-native tooling and agents to help the team investigate attacks and operate models faster.

What we're looking for

• 8+ years of experience developing, evaluating, and deploying machine learning models in a production environment.
• Proven track record of technically leading large, ambiguous ML initiatives from problem definition to production with measurable business impact.
• Deep expertise in machine learning, statistics, model evaluation, and experiment design, specifically with noisy, delayed, or scarce labels.
• Strong software engineering skills with the ability to write tested, maintainable production code.
• Experience designing and operating production ML systems at scale, including data pipelines, real-time inference, deployment, and monitoring.
• Experience setting technical direction across multiple engineers or teams and mentoring engineers to grow their scope.
• Ability to explain complex tradeoffs clearly to engineers, product leaders, and customers to build cross-functional alignment.
• Experience applying ML to fraud, abuse, integrity, trust and safety, identity, or security (preferred).