Senior Fraud Data Scientist — Real-Time Detection

Unchain Data; Menlo Park (CA); Hybrid; USD 187.000 - 220.000; Vollzeit

Benefits dieser Stelle

100% paid health insurance for EMPLOYE

Equity ownership

401(k) matching

Zusammenfassung

Robinhood is seeking a Senior Data Scientist for the Fraud Data Science team, based in Menlo Park with in-person attendance 3 days per week. You will own design and deployment of ML solutions to surface suspicious activity, reduce loss, and improve detection precision. Collaboration with engineering, product, risk, and compliance is essential.

You will apply Python and SQL, build robust pipelines, and drive experimentation to strengthen fraud prevention across the platform.

Qualifikationen

• 5+ years of experience in data science or applied ML, with focus on fraud detection or risk mitigation.
• Advanced Python and SQL proficiency; experience with ML frameworks like XGBoost, LightGBM, or TensorFlow.
• Strong statistical acumen with anomaly detection, pattern recognition, and A/B testing.
• Excellent communication and ability to influence decisions across technical and non-technical audiences.
• Collaborative mindset with proactive approach in fast-paced environments.

Aufgaben

• Design and deploy fraud detection models to protect Robinhood users and assets in real time.
• Analyze behavioral data to uncover emerging fraud vectors and support rapid incident response.
• Develop robust data pipelines and monitoring systems to ensure model accuracy and reliability.
• Partner with engineering and product teams to implement safeguards and user-facing features.
• Guide experimentation strategy and contribute to long-term fraud prevention roadmap.

Kenntnisse

Python

SQL

Fraud detection

A/B testing

Data analysis

Communication

Collaboration

Ambiguity navigation

ML frameworks

Tools

XGBoost

LightGBM

TensorFlow

Jobbeschreibung

Robinhood is seeking a Senior Data Scientist for the Fraud Data Science team, based in Menlo Park with in-person attendance 3 days per week. You will own design and deployment of ML solutions to surface suspicious activity, reduce loss, and improve detection precision. Collaboration with engineering, product, risk, and compliance is essential.

You will apply Python and SQL, build robust pipelines, and drive experimentation to strengthen fraud prevention across the platform.