Data Engineer - Onboarding
Core
Senior Data/ML Engineer owning the end-to-end data and machine learning foundation for Sardine's compliance decisions, including fraud prevention, KYC onboarding, and AML operations.
Role type
Senior hands-on IC Data/ML Engineer
Builds
Production data pipelines, feature platforms, and ML models for real-time fraud detection and identity risk
Domain
Financial crime, fraud prevention, AML, KYC, and identity verification
Deliverable
production ML models | product features
Required skills
Python, SQL, distributed processing (Spark, Beam, Flink), GCP (BigQuery, Dataflow, Dataproc, Vertex AI), ML engineering (feature stores, gradient-boosted trees, model monitoring), data governance (PII, encryption, regional residency), entity resolution, streaming vs batch reconciliation
Preferred skills
Fraud/risk/payments domain experience, high-growth B2B SaaS background, customer-facing ML support, early-hire function building
Technologies
Python, SQL, Apache Beam, Flink, Spark, Airflow, BigQuery, Dataflow, Dataproc, Pub/Sub, Bigtable, Cloud Composer, Vertex AI, Kubeflow, XGBoost, LightGBM, CatBoost, scikit-learn, Docker, Kubernetes, Terraform, dbt, Chronon
Responsibilities
Own data ingestion pipelines for device telemetry, transactions, and KYC signals; build and evolve the feature platform with streaming and batch computation; establish feature correctness through reconciliation and drift monitoring; productionize fraud and identity ML models with automated retraining; engineer KYC/AML risk signals from multi-vendor data; integrate and harden 30+ third-party enrichment providers; manage warehouse and modeling layer in BigQuery; design entity resolution and graph data linking customers and devices; implement safety features like field-level encryption and regional data residency; set technical direction and mentor the team
Seniority
Senior, hands-on IC
