Data Scientist, Trust & Safety
$210,000–$310,000 year
HybridFoster City, California, United States
Job Summary
Own the analytical foundation for Trust & Safety by building reliable datasets, risk models, and anomaly-detection systems to identify phishing, scam hosting, and AI-agent exploitation. Develop predictive models that estimate account and transaction risk, then define thresholds balancing abuse reduction against customer friction and false positives. Design rigorous offline evaluations, shadow-mode tests, and controlled experiments to measure detection quality and user impact across free, paid, and enterprise tiers. Investigate emerging abuse patterns, quantify their economic impact, and partner with Engineering to operationalize findings into detection and escalation workflows. Monitor for model drift, attacker adaptation, and unexpected harm to legitimate users while communicating tradeoffs to technical and non-technical partners.
Required Qualifications
- 5+ years of experience in data science, product analytics, fraud, risk, trust and safety, or a related field
- Strong SQL and Python skills
- Experience working with large behavioral datasets
- Experience building reliable data models or pipelines
- Experience developing and evaluating predictive models
- Experience evaluating experiments or decision systems
- Sound judgment around uncertainty and tradeoffs
- Ability to turn ambiguous data into clear recommendations
- Ability to communicate effectively across technical and non-technical teams
- Comfort working with imperfect labels
- Comfort working with biased samples
- Comfort making high-impact decisions where false positives matter
- Use of AI tools extensively to increase effectiveness
- Maintenance of a high bar for analytical quality
- Monday, Wednesday, and Friday in-office requirement
Desired Qualifications
- Experience building or evaluating anti-abuse, fraud, identity, security, spam, integrity, or content-safety systems at scale
- Built, shipped, and maintained ML models in production (classification, anomaly detection, or risk scoring)
- Experience with feature engineering on behavioral and transaction data
- Experience with threshold selection against precision/recall economics
- Experience with post-launch monitoring
- Experience with graph analysis
- Experience with entity resolution
- Experience with coordinated-behavior detection
- Experience with reputation systems
- Experience with anomaly detection
- Experience with risk scoring
- Experience measuring false positives and enforcement harm
- Experience designing human-review workflows
- Experience using appeals and case outcomes as model feedback
- Familiarity with progressive verification
- Familiarity with KYC
- Familiarity with account trust
- Familiarity with identity providers such as Prove, Persona, Socure, or Stripe Identity
- Experience with causal inference methods such as difference-in-differences, propensity score methods, synthetic control, or uplift modeling
- Experience with a modern data stack such as dbt, BigQuery, Snowflake, Fivetran, Amplitude, Mixpanel, or Segment
- Experience at a consumer platform
- Experience at a developer tool
- Experience at a cloud provider
- Experience at a marketplace
- Experience at a fintech company
- Experience at other product with a meaningful adversarial surface
- You've built AI-powered analytical tools
- You've built investigation systems
- You've built automated detections
- You've built novel measurement approaches
- You have experience with AI-native abuse such as prompt injection, LLM token farming, model extraction, or agent-driven abuse
- You understand freemium, usage-based, or promotional pricing models
- You understand the abuse incentives they create
- You've worked directly with operational review teams
- You can translate analytical signals into practical playbooks
- You can translate analytical signals into queues
- You can translate analytical signals into escalation paths
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.