Data Engineer - Onboarding

Stack

Responsibilities

• ▹Own the data ingestion layer for device telemetry, transaction events, KYC/identity signals and third-party enrichment, designing streaming (Pub/Sub, Apache Beam on Dataflow, Flink) and batch pipelines (Python, Airflow on Cloud Composer, Spark on Dataproc)
• ▹Build and evolve the feature platform, where the same Chronon feature definitions are computed by Flink for streaming and Spark for batch, with windows from one hour to 300 days, served to the rules engine and models under a sub-second budget
• ▹Establish feature correctness as an engineering discipline: streaming-versus-batch reconciliation, recomputation tests against the warehouse, train/serve parity checks and drift monitoring
• ▹Productionize fraud and identity ML models: training pipelines on Vertex AI and Kubeflow, gradient-boosted and tree-based models (XGBoost, LightGBM, CatBoost, scikit-learn), hyperparameter search, SHAP-based explanations and score normalization
• ▹Build automated retraining, champion/challenger promotion and rollback machinery
• ▹Engineer KYC, AML and identity risk signals: document verification, sanctions/PEP/adverse-media screening, email and phone risk, synthetic identity indicators, bank and account verification, periodic customer due diligence
• ▹Integrate and harden new data sources, including 30+ third-party enrichment providers called in parallel on the request path and the cross-client consortium network, owning failover, timeout budgets, graceful degradation, caching and cost
• ▹Own the warehouse and modeling layer in BigQuery: partitioning, staging-to-mart layers, training datasets and the in-flight migration off dbt onto scheduled SQL and Python pipelines
• ▹Design the entity resolution and graph data linking customers, devices, emails, phones, cards, bank accounts and crypto addresses across clients, including large-scale connected-components work
• ▹Make the platform safe by construction: field-level encryption for sensitive identifiers, regional data residency enforced in pipeline definitions, PII handling and deletion paths, and feature-level gating so a bad signal can be turned off without a deploy
• ▹Set technical direction and raise the team's ceiling: write design docs, run reviews, mentor engineers and data scientists, decide what to build versus buy

Requirements

• ▹8+ years building production data and ML systems, with real ownership of both the pipeline and the model side
• ▹Has shipped models that made consequential automated decisions, not just dashboards
• ▹Deep Python and strong SQL
• ▹Fluency in a distributed processing framework (Spark, Beam or Flink) and streaming semantics: windowing, watermarks, late data, exactly-once versus at-least-once
• ▹Hands-on experience with a modern cloud data stack: GCP strongly preferred (BigQuery, Dataflow, Dataproc, Pub/Sub, Bigtable, Composer, Vertex AI) or AWS equivalents, plus Docker, Kubernetes, Terraform and CI/CD
• ▹Practical ML engineering depth: feature stores and pipelines, training/serving skew, gradient-boosted tree models, class imbalance and rare-event modeling, threshold and cost-sensitive tuning, model monitoring, drift detection and explainability
• ▹Experience with high-volume, low-latency serving where a feature fetch has a few hundred milliseconds and no retry budget
• ▹Domain experience in fraud, risk, payments, lending or identity/KYC, or the demonstrated ability to get fluent in a regulated domain fast
• ▹Understanding of why label latency, feedback loops and adversarial drift make fraud modeling different from ordinary supervised learning
• ▹Comfort with data governance in a regulated environment: PII, encryption, access control, regional data residency, auditability
• ▹Strong written communication, able to explain a modeling tradeoff to a fraud analyst and a pipeline design to a backend engineer

Nice to have

• ▹Experience supporting customer-facing ML: bring-your-own-model integrations, model explainability for adverse action or regulatory review, shadow/challenger scoring frameworks

Soft skills

What we offer

• ▹Work from anywhere in a remote-first culture
• ▹Role based in the United States or Canada
• ▹Hubs in the Bay Area, NYC, Austin, Toronto and São Paulo
• ▹Flexible schedule: performance is valued, not hours worked

About the company

Sardine is the leading agentic risk platform for fighting financial crime, unifying data across risk teams to stop fraud in real time and automate fraud and AML operations. Customers include FIS, GoDaddy, Intuit, Edward Jones, ZoomInfo and Checkout.com.