Data Engineer - Onboarding
Sardine · Remote · North America · United States · Canada ·
COMPENSATION
$150k – $205k
Listed on the employer's job board (Ashby)
- Senior Data/ML Engineer
- Remote (US/Canada)
- Python + SQL + Spark
- GCP Cloud Stack
- Fraud & KYC Domain
You will own the data ingestion, feature engineering, and model productionization that power Sardine’s compliance decisions. Working at the intersection of data and ML engineering, you will design streaming and batch pipelines while ensuring feature correctness and model reliability in production.
What you'll do
- Design streaming and batch pipelines for device telemetry and transaction events
- Build feature platforms using Chronon, Flink, and Spark with sub-second serving
- Implement streaming-versus-batch reconciliation and drift monitoring tests
- Productionize fraud models using Vertex AI, Kubeflow, and gradient-boosted trees
- Engineer KYC and AML signals from multi-vendor data sources
- Manage integration of third-party enrichment providers with failover logic
- Own BigQuery warehouse structure and migrate off dbt to scheduled pipelines
- Design entity resolution graphs linking customers, devices, and accounts
- Enforce field-level encryption and regional data residency in pipelines
- Mentor engineers and set technical direction for data infrastructure
What you'll need
- 8+ years building production data and ML systems with full ownership
- Deep proficiency in Python, SQL, and distributed frameworks like Spark or Flink
- Experience with GCP stack including BigQuery, Dataflow, and Vertex AI
- Practical knowledge of feature stores, training/serving skew, and model monitoring
- Ability to handle high-volume, low-latency serving with strict timeout budgets
- Domain experience in fraud, risk, payments, or identity/KYC verification
- Understanding of data governance, PII handling, and regulatory compliance
- Strong written communication skills for cross-functional collaboration
Nice to have
- Experience supporting customer-facing ML integrations
- Background in high-growth B2B SaaS environments
- History as an early data hire building functions from scratch
Stack
- Python
- SQL
- Apache Beam
- Flink
- Spark
- Airflow
- Chronon
- BigQuery
- Vertex AI
- Kubeflow
- XGBoost
- LightGBM
- CatBoost
- scikit-learn
- GCP
- Docker
- Kubernetes
- Terraform
How you'll work
- Remote-first culture within US or Canada
- Must maintain home base in hiring country
- Flexible schedule focused on performance not hours
- No office reporting required
What you get
- Generous cash and equity compensation
- Early exercise options including pre-vested
- Flexible paid time off and year-end break
- Health, dental, and vision coverage
- 4% matching in 401k or RRSP
- MacBook Pro provided
- One-time home office setup stipend
- Monthly meal and social meet-up stipends
- Annual health, wellness, and learning stipends