Replit

1 day ago

Data Scientist, Trust & Safety

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 3 hours agoStatus: Live

Job Summary

Build Trust & Safety and Anti-Abuse measurement systems for an AI-native abuse surface. Turn behavioral, identity, payment, infrastructure, and content signals into datasets, dbt models, risk models, and detection decisions. Design offline evaluations, shadow-mode tests, holdouts, and experiments to quantify detection quality and user impact. Define thresholds and decision frameworks, monitor drift and attacker adaptation, and partner with Support and Legal to improve enforcement, appeals, and feedback loops.

Location: United States

Workplace: Hybrid

Employment Type: Full time

Job Function: Data Science & Machine Learning

Seniority: Mid level

Key Responsibilities

•Own Trust & Safety analytical foundations, including abuse prevalence, fraud loss, false-positive/false-negative rates, time-to-detect/mitigate, and appeal/reversal metrics.
•Build reliable datasets and dbt models connecting product events, identity signals, payments, infrastructure usage, content classifications, enforcement actions, appeals, and support outcomes.
•Develop and evaluate risk models, rules, and anomaly-detection systems for threats like phishing, scam hosting, cryptomining, token farming, and payment fraud.
•Design offline evaluations, shadow-mode tests, holdouts, and controlled experiments to measure detection quality and policy/user impact.
•Define thresholds and decision frameworks balancing abuse reduction, economic loss, customer friction, and false positives; investigate new abuse patterns and monitor drift and attacker adaptation.

Pay and Benefits

Salary: USD 210,000 - 310,000 annually

Equity and Bonus:Equity

Perks:Health InsuranceDentalVision401kLife InsuranceDisabilityPaid ParentalPaid LeaveWellness Stipend

Key Requirements

•5+ years of experience in data science, product analytics, fraud, risk, trust and safety, or a related field.
•Strong SQL and Python skills with experience building reliable data models or pipelines from large behavioral datasets.
•Experience developing and evaluating predictive models, experiments, or decision systems with good judgment around uncertainty and tradeoffs.
•Ability to turn ambiguous, imperfect data (biased samples, missing labels) into clear recommendations and communicate effectively with technical and non-technical partners.
•Comfort with high-stakes trust & safety decisions where false positives matter, using AI tools while maintaining analytical quality.

Experience:5+ yearsTrust and safetyFraudRiskProduct analytics

Skills:Adversarial thinkingUncertainty quantificationCommunicationAnalytical quality

Tech Stack:SQLPythonDbtAIMachine learningAnomaly detectionRisk scoringGraph analysisEntity resolutionKYCProvePersonaSocureStripe IdentityDifference-in-differencesPropensity score methodsSynthetic controlUplift modelingBigQuerySnowflake

Company Brief

Replit

Provides a browser-based integrated development environment (IDE) and collaborative coding platform that lets developers write, run, and deploy code instantly across many languages and frameworks.

Industry: Developer Tools

Company Size: Large (251 to 1,000 employees)

Growth: Scaleup

Headquarters: San Francisco, United States

Founded: 2016

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

Replit

1 day ago

Data Scientist, Trust & Safety

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 3 hours agoStatus: Live

Job Summary

Location: United States

Workplace: Hybrid

Employment Type: Full time

Job Function: Data Science & Machine Learning

Seniority: Mid level

Key Responsibilities

•Own Trust & Safety analytical foundations, including abuse prevalence, fraud loss, false-positive/false-negative rates, time-to-detect/mitigate, and appeal/reversal metrics.
•Build reliable datasets and dbt models connecting product events, identity signals, payments, infrastructure usage, content classifications, enforcement actions, appeals, and support outcomes.
•Develop and evaluate risk models, rules, and anomaly-detection systems for threats like phishing, scam hosting, cryptomining, token farming, and payment fraud.
•Design offline evaluations, shadow-mode tests, holdouts, and controlled experiments to measure detection quality and policy/user impact.
•Define thresholds and decision frameworks balancing abuse reduction, economic loss, customer friction, and false positives; investigate new abuse patterns and monitor drift and attacker adaptation.

Pay and Benefits

Salary: USD 210,000 - 310,000 annually

Equity and Bonus:Equity

Perks:Health InsuranceDentalVision401kLife InsuranceDisabilityPaid ParentalPaid LeaveWellness Stipend

Key Requirements

•5+ years of experience in data science, product analytics, fraud, risk, trust and safety, or a related field.
•Strong SQL and Python skills with experience building reliable data models or pipelines from large behavioral datasets.
•Experience developing and evaluating predictive models, experiments, or decision systems with good judgment around uncertainty and tradeoffs.
•Ability to turn ambiguous, imperfect data (biased samples, missing labels) into clear recommendations and communicate effectively with technical and non-technical partners.
•Comfort with high-stakes trust & safety decisions where false positives matter, using AI tools while maintaining analytical quality.

Experience:5+ yearsTrust and safetyFraudRiskProduct analytics

Skills:Adversarial thinkingUncertainty quantificationCommunicationAnalytical quality

Company Brief

Replit

Provides a browser-based integrated development environment (IDE) and collaborative coding platform that lets developers write, run, and deploy code instantly across many languages and frameworks.

Industry: Developer Tools

Company Size: Large (251 to 1,000 employees)

Growth: Scaleup

Headquarters: San Francisco, United States

Founded: 2016

Website LinkedIn