Machine Learning Engineer

### Who you are
- 5+ years of experience in machine learning engineering, data science, data engineering, or a related technical field
- Strong experience in feature engineering, particularly with large-scale transactional or time-series datasets
- Proficiency in Python, SQL, and modern ML frameworks (e.g., PyTorch, XGBoost, sci-kit learn)
- Experience building production ML pipelines and deploying models in cloud environments
- Strong understanding of data modeling, forecasting, and statistical analysis
- Clear and effective communication skills when working with product, engineering, and business stakeholders
- Demonstrated ability to execute end-to-end: from raw data exploration to production ML implementation
- Software engineering proficiency with a sensible adherence to good software design patterns
- Experience with Plaid or similar financial data providers
- Background in credit risk modeling, underwriting features, or financial signal extraction
- Familiarity with MLOps tools (e.g., MLflow, SageMaker, Feature Stores, Airflow)
- Experience building or contributing to internal Data Science platforms
- Knowledge of explainable ML techniques and regulated-model requirements
- Prior work in fintech, credit, or payments

### What the job involves
- As a Machine Learning Engineer on Clair’s Data team, you will be responsible for transforming diverse financial data sources, including but not limited to Plaid transactions, into production-grade features, predictive signals, and modeling pipelines that power Clair’s credit and underwriting systems
- Your work will focus on building the core feature layer that our credit models depend on: extracting structure from messy financial data, designing robust predictive features, forecasting key user-level events (such as income timing or financial stability indicators), and ensuring that these features are efficiently deployed, monitored, and continuously improved
- In addition to hands-on modeling and feature engineering, you will contribute to the development of Clair’s Data Science platform – building tooling, automation, and infrastructure that make it easier to train, deploy, and monitor ML systems at scale
- This role is ideal for someone who loves crafting meaningful features out of raw data, scaling ML systems in production, and driving the technical foundations of a modern financial ML stack
- Engineer high-quality features from financial and behavioral data to support credit modeling
- Build and maintain scalable pipelines for feature computation, income detection, and financial signal extraction
- Develop forecasting and predictive models for income timing, user stability, and financial behavior patterns
- Deploy, monitor, and optimize ML models and feature pipelines in production using AWS, Snowflake, or other tooling
- Contribute to the development of Clair’s Data Science platform, including model deployment workflows, feature stores, and monitoring systems
- Collaborate with engineering, product, and risk teams to understand their workflows and ensure data products have high availability for their use cases
- Prototype new modeling techniques and evaluate their impact on credit and underwriting performance
- Communicate findings and technical decisions clearly to both technical and non-technical stakeholders

### Benefits
- 100% Medical, Dental, & Vision Coverage, with option to extend to your family
- Fully-paid parental leave
- Company-sponsored 401k, HSA, and FSA
- Unlimited vacation
- Work from home setup allowance
- Access to your earnings every day on Clair
- Company-sponsored short-term and long-term disability insurance