R
$210,000 – $310,000
Listed on Replit’s own careers site. You apply with them directly — we never stand between you and the employer.
What this role is
This role builds Replit's fraud detection and abuse prevention systems from the ground up, analyzing behavioral, payment, and infrastructure signals to protect users while keeping friction low for legitimate users. It suits data scientists who excel at working with imperfect, adversarial datasets and can move rapidly from raw signals to actionable recommendations for engineering and policy teams.
Our summary, not Replit’s wording. The full posting is on their site.
Skills this role names
- Amplitude
- Anomaly Detection
- Dialectical Behavior Therapy (DBT)
- Google BigQuery
- Mixpanel
- Python
- Segment
- Snowflake
- SQL
Log in to see which of these are already on your profile.
What they ask for
Required
- 5+ years in data science, product analytics, fraud, risk, trust and safety, or related field
- Strong SQL and Python with experience on large behavioral datasets and data modeling
- Experience developing and evaluating predictive models, experiments, or decision systems
- Ability to communicate ambiguous data insights clearly to technical and non-technical teams
- Comfort working with imperfect labels, biased samples, and high-impact decisions where false positives matter
- Regular use of AI tools to increase effectiveness while maintaining analytical quality
Nice to have
- Experience building anti-abuse, fraud, identity, security, or content-safety systems at scale
- Production ML experience with classification, anomaly detection, or risk scoring including feature engineering and post-launch monitoring
- Graph analysis, entity resolution, coordinated-behavior detection, or reputation systems
- Experience measuring false positives, designing human-review workflows, or using appeals as model feedback
- Familiarity with progressive verification, KYC, or identity providers like Prove, Persona, or Socure
- Causal inference methods such as difference-in-differences or synthetic control
- Experience at consumer platforms, developer tools, marketplaces, or fintech with adversarial surfaces
- Built AI-powered analytical tools or investigation systems
- Experience with AI-native abuse patterns like token farming or LLM exploitation
- Understanding of freemium or usage-based pricing abuse incentives
- Direct experience with operational review teams and translating signals into playbooks