Data Scientist Customer Experience

Transmit Security•Boston, MA

7d•$160,000 - $200,000

About The Position

Transmit Security is a cross-channel identity and orchestration platform designed to simplify, accelerate, and reduce the cost of identity-related projects, such as authentication, authorization, fraud prevention, and new account opening. The platform provides cutting-edge capabilities by fusing Identity Management and Fraud Prevention, allowing businesses to balance customer experience with fraud reduction while enhancing security and agility. Team Mission The Customer Experience Data Science function partners with customers and internal stakeholders to translate fraud signals into measurable business outcomes: improved detection efficacy, reduced false positives, faster time-to-mitigation, and product feedback loops that scale across tenants. The Senior Data Scientist operates as a technical lead, owning complex investigations and shaping repeatable analytical and decisioning frameworks. Role Summary The Data Scientist on the Customer Experience team is responsible for leading high-impact customer investigations, driving detection and decisioning improvements (rules/features/model recommendations), and influencing product direction through evidence-based insights. This role requires a blend of fraud domain expertise, strong applied analytics/ML, and executive-level communication in customer-facing contexts.

Requirements

6+ years in data science / applied analytics roles with increasing scope and ownership; fraud/risk/identity/security experience strongly preferred.
Expert-level SQL and strong Python for analytics and production-grade analysis (testing, modularity, version control habits).
Experience operating in customer-facing environments, including executive communication and handling escalations with calm, credible technical leadership with proven ability to lead end-to-end analytical initiatives.
Deep competence in statistics and evaluation: hypothesis testing, segmentation, regression/classification metrics time series / anomaly detection concepts experimental design and causal inference fundamentals
Bachelor’s degree in a quantitative field required; advanced degree preferred (MS/PhD).
Hands-on experience with real-time decisioning systems, streaming/event-based analytics, and latency-aware detection constraints.
Familiarity with modern ML methods used in fraud: supervised classifiers, graph/ring detection approaches, anomaly detection, and model monitoring.
Experience deploying or operationalizing models (MLOps exposure), including monitoring, drift detection, and retraining governance.
Experience with identity/authentication ecosystems (MFA modalities, risk-based authentication, device intelligence, bot defense signals).

Responsibilities

Lead complex, multi-signal investigations (e.g., account takeover, automation, fraud rings, API abuse) and produce clear, actionable remediation plans.
Serve as the CX technical authority in escalations, guiding hypothesis formation, analysis strategy, and root-cause conclusions.
Translate customer context (risk tolerance, user base, operational constraints, compliance) into measurable detection and tuning objectives.
Identify emerging fraud patterns and cross-tenant trends; conduct quarterly intelligence briefs for customers and recommended mitigations.
Design and recommend detection strategies combining rules, features, and (where applicable) model-driven scoring to reduce fraud while controlling false-positive costs.
Develop reusable feature definitions and tuning approaches that can be applied across customers (not only one-off tenant fixes).
Partner with engineering and products to shape product roadmap priorities, improve explainability and investigation tooling (e.g., “why did this fire,” attribution, drill-down paths).
Define and own CX measurement systems: detection quality, false-positive impact, operational metrics, customer outcomes, and performance over time.
Lead offline evaluation and backtesting methodologies for fraud controls and customer configuration changes.
Drive experimentation practices (A/B where feasible, quasi-experimental, pre/post with controls) and ensure results are decision-grade.
Detect data drift and performance degradation signals; propose retraining triggers and/or mitigation plans in partnership with ML/Engineering.
Create “investigation packs” for R&D: evidence, root cause hypothesis, recommended technical changes, and measurable acceptance criteria.
Mentor and develop other DS/analysts on CX through playbooks, code reviews, investigation standards.
Partner with GTM teams to quantify customer value, communicate outcomes, and support renewals/expansions through data-backed narratives.