Plaid
Machine Learning Engineer - Credit
About this role
Plaid's Data team seeks an experienced Machine Learning Engineer to design and deploy scalable ML solutions for credit underwriting and financial services. You'll own the full model lifecycle from training to production serving, collaborating across teams to build cash flow-based underwriting and drive high-impact fintech applications.
What you'll do
- Design, build, and deploy scalable ML systems for credit use cases in production environments
- Experiment with state-of-the-art modeling techniques including NLP, anomaly detection, and time series forecasting
- Own machine learning models across full lifecycle: offline training, online serving, and monitoring
- Collaborate with engineers on signal ingestion and model productionization
- Work on both early-stage (0-1) and scaling problems (1-10) across the credit space
- Define ML roadmap with cross-functional teams using data-driven decision-making
What they're looking for
- Machine learning model development and deployment
- Python and Spark programming
- Fintech lending domain knowledge
- Distributed systems and data-intensive backend applications
- NLP, anomaly detection, and time series forecasting
- Model monitoring and online serving
- Data analysis and experimentation
- Cross-functional collaboration and communication
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Plaid
Plaid builds infrastructure that connects users to their financial data and enables secure financial transactions through APIs and integrated experiences. The company is hiring Full Stack Software Engineers, Backend Engineers, Security Engineers, and Sales Engineers to develop and support its platform for millions of users.
- Website
- plaid.com
Likely interview questions
- Can you walk us through a production ML model you've built in fintech lending and how you approached its deployment and monitoring?
- Describe your experience building or scaling ML systems in distributed environments—what challenges did you face?