Sardine
Data Engineer - Onboarding
About this role
Sardine seeks a Senior Data/ML Engineer to architect and own end-to-end data pipelines and ML infrastructure powering real-time fraud detection and compliance decisions. You'll design streaming and batch systems, build feature platforms, productionize models, and establish data quality disciplines across a fast-growing fintech risk platform.
What you'll do
- Design and maintain data ingestion pipelines (Pub/Sub, Beam, Flink, Spark, Airflow) for device telemetry, transactions, KYC signals, and third-party enrichment
- Build and evolve the feature platform using Chronon for streaming/batch feature computation with sub-second serving latency
- Establish feature correctness practices including reconciliation testing, drift monitoring, and train/serve parity validation
- Productionize ML models on Vertex AI and Kubeflow, managing training, hyperparameter tuning, champion/challenger promotion, and automated retraining
- Engineer KYC, AML, and identity risk signals from multi-vendor data sources into trainable features
- Design entity resolution and graph infrastructure linking customers, devices, accounts, and addresses across clients
What they're looking for
- Data pipeline orchestration (Airflow, Cloud Composer, Apache Beam, Flink)
- Big data processing (Spark, Dataproc, PySpark)
- Machine learning model deployment (Vertex AI, Kubeflow, XGBoost, LightGBM, scikit-learn)
- Data warehouse design (BigQuery, partitioning, staging-to-mart patterns)
- Feature engineering platforms (Chronon or similar)
- Python and production-grade code quality
- Streaming systems design and event-driven architecture
- Graph data structures and entity resolution at scale
Benefits
- Remote-first culture with flexibility to work from anywhere in US/Canada
- High-impact role setting technical direction for fraud ML infrastructure
- Direct collaboration with data scientists, backend engineers, and fraud analysts
- Performance-based work environment focused on results, not hours
- Opportunity to build systems serving billions of profiled devices and millions of businesses
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Sardine
Sardine builds AI-powered fraud prevention and compliance solutions that help organizations detect and prevent financial crime. The company is hiring Data Engineers, Machine Learning Engineers, DevOps Engineers, and Forward Deployed AI Engineers to develop their data infrastructure, ML systems, and client-facing AI solutions.
- Website
- sardine.ai
Likely interview questions
- Walk us through how you'd design a streaming feature pipeline that guarantees consistency between real-time and batch-computed features at different aggregation windows.
- Describe a time you caught and fixed a production data quality issue—what monitoring would have caught it earlier?