Machine Learning Engineer

About the role

As a Machine Learning Engineer at Sift you will bridge data science and large‑scale distributed systems. You will build end‑to‑end pipelines that extract signals, train custom models per merchant and serve low‑latency predictions at production scale. The role also involves maintaining an automated ML ecosystem that continuously recalibrates models using streaming global telemetry.

Key responsibilities

• Design, build and deploy online ML models—including ensembles, deep learning, transformer and graph‑based architectures—to detect evolving fraud vectors in real time.
• Engineer high‑frequency time‑series features from over a trillion behavioral events, optimizing for low‑latency extraction.
• Maintain and enhance automated model training and deployment infrastructure, ensuring CI/CD of new models.
• Write high‑performance code to minimise scoring latency and scale ML services across distributed databases.
• Collaborate with Core Infrastructure, Product Management and Data Science teams to translate business fraud patterns into algorithmic solutions.

Required profile

• 4+ years of professional experience building and deploying large‑scale ML models in high‑traffic production environments.
• Strong proficiency in Java or Scala for backend services and Python for data analysis and prototyping.
• Hands‑on experience with Databricks and big‑data frameworks such as Apache Spark, Flink or Hadoop, and NoSQL stores like Bigtable.
• Deep understanding of statistical modelling, probability and common ML algorithms (e.g., XGBoost, Random Forests, Neural Networks, clustering).
• Ability to design systems that handle data consistency, pipeline failures and performance constraints in a multi‑tenant GCP environment.

Required skills

• Java
• Scala
• Python
• Apache Spark
• Apache Flink
• Hadoop
• Databricks
• Google Cloud Platform
• Bigtable
• XGBoost
• Random Forests
• Neural Networks
• Clustering techniques
• Apache Kafka
• Docker
• Kubernetes