Sardine
Data Engineer - Onboarding
$150K–$205K
North America +2 · Remote · Full-time · Posted Jul 30, 2026
- Location
- North America
United States
Canada - Experience
- 8+ years building production data and ML systems.
About the job
Own and develop the data pipelines, features, and production ML systems behind Sardine’s onboarding, fraud, identity, and compliance decisions.
What you'll do
- Build and operate streaming and batch data pipelines, feature infrastructure, and warehouse models.
- Productionize fraud and identity ML, including model training, deployment, monitoring, retraining, and rollback.
- Develop KYC and entity-resolution signals, integrate data providers, and guide technical direction while mentoring the team.
What they ask for
- 8+ years building production data and ML systems, with ownership of both pipelines and models; shipped models used for consequential automated decisions.
- Deep Python and strong SQL, plus fluency in Spark, Beam, or Flink and understanding of streaming semantics.
- Hands-on modern cloud data stack experience, plus Docker, Kubernetes, Terraform, and CI/CD.
- Practical ML engineering depth, high-volume low-latency serving experience, and familiarity with regulated data governance.
Nice to have
- GCP experience; AWS equivalents are also accepted.
- Experience with customer-facing ML, high-growth B2B SaaS, or as an early data/ML hire.
Pay
$150K – $205K USD base salary
Tools
Python, SQL, Pub/Sub, Apache Beam, Flink, Spark, Airflow, BigQuery
AI focus
Build and productionize fraud, identity, and KYC ML models; develop feature pipelines, automated retraining and promotion workflows, model monitoring, and entity resolution.
Model-written summary · the original posting is authoritative