About the role

Software Engineer developing and maintaining secure ML infrastructure and automation at Yelp. Collaborating with cross-functional teams to protect users from fraud and spam.

Responsibilities

Design, build, and maintain secure, compliant ML infrastructure and automation adapted for high-sensitivity environments.
Develop and productionize machine learning and data pipelines serving real-time models that fight fraudulent traffic, spam, and bots.
Extract valuable signals from massive datasets, using your expertise to turn raw data into actionable insights.
Dive deep into data to uncover patterns indicative of suspicious or fraudulent behavior and iterate on detection signals.
Drive adoption of best practices in MLOps (model versioning, CI/CD for ML, monitoring) and ensure robust privacy/data protection controls.
Collaborate closely with teams across Yelp, including Core ML, Security, and Product, to proactively defend our users and business metrics.
Provide technical mentorship and contribute to the continuous improvement of engineering standards and experimentation processes.

Solid foundation in software engineering and machine learning/data engineering best practices.
Experience designing or adapting ML infrastructure, MLOps tooling, and data pipelines in Python (e.g., pandas, NumPy, scikit-learn, TensorFlow, XGBoost), Spark, AWS (e.g., S3, Redshift), and modern databases (e.g., SQL/NoSQL).
Demonstrated ability to build large-scale, real-time distributed systems for detecting abuse, fraud, or adversarial behavior.
Deep understanding of privacy, data protection, secure engineering, and access control within ML systems.
Comfort working independently in a fast-paced, ambiguous environment, with the curiosity and tenacity to tackle evolving problems.
Excellent communication skills and a collaborative mindset, especially when handling sensitive projects under NDA.
Bonus: Experience with Kubernetes, MLflow, Kubeflow, Airflow, Scala, MapReduce, Flink, Cassandra, or related technologies.