Machine Learning Engineer
$140k - $190k • San Francisco, California • FullTime
Posted 10d ago
Job Location
San Francisco, California
Tech Stack
Remote Work Policy
On-site
Employment Type
FullTime
Categories
Machine Learning Engineer
About the job
As a Machine Learning Engineer at Sift, you will bridge the gap between data science and large-scale distributed systems. You will build end-to-end pipelines that extract signals, train custom models per merchant, and serve predictions at production scale with low latency. You will work on an automated machine learning ecosystem that dynamically recalibrates models based on streaming global telemetry data.
Responsibilities
- Design, build, and deploy online machine learning models, including ensemble methods, deep learning, transformer architectures, and graph-based models, to detect evolving fraud vectors in real time.
- Engineer high-frequency time-series features from over 1 trillion behavioral events, optimizing for low-latency signal extraction and pattern recognition.
- Maintain and enhance automated model training and deployment infrastructure, ensuring frictionless CI/CD of newly trained models.
- Write high-performance code to minimize scoring latency at runtime, ensuring ML services scale seamlessly across distributed databases.
- Collaborate with Core Infrastructure, Product Management, and Data Science teams to translate business-level fraud patterns into algorithmic solutions.
Requirements
- 4+ years of professional experience building and deploying large-scale machine learning models into high-traffic production environments.
- Strong proficiency in Java or Scala, and Python.
- Practical experience with Databricks and big data processing frameworks like Apache Spark, Apache Flink, or Hadoop.
- Experience working with NoSQL data stores like Bigtable.
- Deep understanding of statistical modeling, probability, and standard machine learning algorithms (e.g., XGBoost, Random Forests, Neural Networks, Clustering).
- Ability to reason through data consistency, pipeline failures, and performance constraints in a distributed, multi-tenant cloud environment (GCP).