Senior Machine Learning Engineer - Fraud and Risk

The Data Platform team works closely with all teams and cross-functional partners (including product, engineering, and data analysts) to build a foundational data stack powering business analytics.

We are looking for someone to play a mission-critical role in designing and building the machine models for risk, fraud, recommendation, and personalization that powers Bolt. This should be someone with experience, creativity, and passion for producing world-class technology. Companies and consumers alike will rely heavily on what you build, and you’ll have a ton of trust and responsibility. If challenges excite you, and you’re ready for a large one, let us know.

What you will be doing:

• Build production ready machine learning models; your models will be the engine that powers online commerce through Bolt
• Establish reusable frameworks to streamline model building, deployment and monitoring, incorporating comprehensive monitoring, logging, tracing, and alerting mechanisms
• Conduct data analysis to determine which policies we adopt and help inform strategic growth
• Build machine learning infrastructure, data pipelines and production ready services to serve live traffic
• Collaborate with Product Managers to ensure proper tracking of algorithmic performance KPIs and prioritize performance improvements based on effort and impact
• Work with other teams at Bolt to engineer new features for models or new product features that help improve Bolt business

What would set you up for success:

• Minimum of three years’ post-secondary education or relevant work experience, along with minimum of two years’ software development experience with Python and SQL
• Minimum of two years’ experience using PyTorch, Tensorflow, Spark ML for building pipelines to deploy NLP and deep learning models into production in a cloud (AWS, GCP, Azure) environment
• Thorough understanding of machine learning fundamentals and methodologies
• Experience building and deploying machine learning models in an applied setting
• Strong understanding of how to build scalable ML systems supporting online and offline applications
• Familiarity with best practices of lifecycle management for ML models in industry

What would set you apart:

• Retail and/or Martech experience in building large-scale personalization and recommendation systems in a consumer-based setting.
• Experience with big data tools like Spark, Kafka, BigQuery, Dataflow, Apache Beam, Pubsub, Cloud Functions, EMR, S3, Glue, Kinesis Firehose, Lambda; a Linux environment
• Industry experience in building large-scale recommendation systems in a consumer-based setting.

Estimated cash compensation: $180k-240k plus equity DOE