SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 270,000 - 290,000 / annual
Pipe is seeking a Senior Data Scientist to design, develop, and deploy machine learning and statistical models that forecast customer cash flows, credit risk, and other measures of business health. You will use experimentation and statistical methods to test product, pricing, and underwriting changes while improving customer experience on the platform.
Key responsibilities include exploring and analyzing large datasets to identify relevant signals, engineering features, and uncovering insights that inform model and product design. You will prototype and ship model-driven features and data products that provide value to customers and internal stakeholders. The role involves researching and evaluating advanced deep learning architectures and training techniques, including transformer-based and recurrent models, and implementing innovations such as mixture of experts, semi-supervised, and generative approaches to improve core underwriting algorithms.
You will monitor models in production, investigate performance issues, and retrain or update models as needed in collaboration with engineering, product, and risk teams.
Required qualifications include a Master's degree in Computer Science, Data Science, or a closely related discipline, plus 3+ years as a Data Scientist or in a related role. You must have 3+ years of experience building and optimizing deep learning models for forecasting, classification, and ranking; designing and training deep learning models for sequence and time series data (including transformer-based architectures and RNNs); executing end-to-end machine learning projects from data collection through production deployment and monitoring; applying machine learning, deep learning, optimization, statistics, and probability theory; using statistical and causal inference methods; designing and executing A/B tests and experiments in production environments; and working with large-scale data processing using modern frameworks (PyTorch, TensorFlow, JAX, scikit-learn, MXNet, Spark) and cloud platforms (AWS, GCP).
This is a fully remote position available anywhere in the United States, with headquarters in San Francisco, CA.
