Trust and Safety Data Scientist
Replit is an agentic AI software-creation platform for creating, launching, and growing apps, websites, tools, and businesses through natural language.
Funding history
About Replit
Replit combines an AI agent with integrated application infrastructure—including authentication, databases, hosting, monitoring, integrations, and enterprise controls—to let users build and deploy software from one workspace.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will build the analytical foundation for trust and safety, connect data across product, identity, payment, and enforcement systems, and develop risk models and anomaly detection. You will evaluate policies and detections, investigate emerging abuse, monitor model drift, and communicate evidence-based recommendations to technical and non-technical partners.
Requirements
- 5+ years of data-science, product-analytics, fraud, risk, or trust-and-safety experience
- SQL expertise
- Python expertise
- Experience with large behavioral datasets
- Experience building data models or pipelines
- Experience developing and evaluating predictive models, experiments, or decision systems
- Experience communicating recommendations across technical and non-technical teams
- Experience working with imperfect labels and biased samples
- Experience using AI tools in analytical workflows
Responsibilities
- Own trust-and-safety measurement and analytics
- Build datasets and dbt models across product, identity, payment, and enforcement signals
- Develop and evaluate risk models, rules, and anomaly-detection systems
- Design offline evaluations, shadow-mode tests, holdouts, and controlled experiments
- Define decision thresholds that balance abuse reduction and user friction
- Investigate emerging abuse patterns and coordinated behavior
- Embed risk signals into detection, review, and escalation workflows
- Improve case-review, appeal, and feedback-loop processes
- Build monitoring for model drift, attacker adaptation, and data-quality failures
- Communicate findings and decision tradeoffs to partners
Benefits
- Equity
- 401(k) program with 4% match for US employees
- Health insurance
- Dental insurance
- Vision insurance
- Life insurance
- Short-term disability
- Long-term disability
- Paid parental leave
- Paid medical leave
- Paid caregiver leave
- Flexible time off
- Holidays
- Commuter benefits for in-office US employees
- Monthly wellness stipend
- In-office setup reimbursement
- Quarterly team gatherings
- In-office amenities