The opportunity
At Gusto, we're on a mission to grow the small business economy. We handle the hard stuff — payroll, health insurance, 401(k)s, and HR — so owners can focus on their craft and their customers.
What you'll do
Build and deploy machine learning models to identify, assess and mitigate risks
Responsible for driving research in the problem space, working with: stakeholders to understand model requirements, developing the model from scratch, deploying the model alongside your engineering counterparts, and monitoring and maintaining the model’s performance over time
Partner with Engineering, Design, and Product counterparts in Identity and: Risk to solve complex cross functional problems
Develop scalable frameworks and libraries that enhance and contribute to the: team’s core analysis and modeling capabilities, including through the integration of LLMs to improve data processing, analysis, and insights.
Identify new opportunities to leverage data to improve Gusto’s products and: help risk management team to understand business requirements and develop tailored solutions
Present and communicate results to stakeholders across the company
What they're looking for
- + years of experience conducting statistical analyses on large datasets and: deep domain knowledge in machine learning and artificial intelligence, including familiarity with Large Language Models (LLMs) and their applications. This could mean either a MS or PhD in a quantitative field with at least 5 years experience in a business environment, or BS or Data Science Bootcamp graduate with at least 8 years of experience working as a data scientist or a machine learning engineer in a business setting.
- Proven experience in credit risk modeling or fraud risk modeling using: logistic regression, random forest, Xgboost or neural networks, along with a strong understanding of AI-based approaches and the potential of LLMs to enhance traditional models.
- Experience applying a variety of statistical and modeling techniques using: Python, R or another statistical modeling language, as indicated by familiarity with many of the following techniques - predictive modeling, anomaly detection, ensemble methods, natural language processing (NLP, optional). Basic understanding of LLMs and their applications.
- Strong programming skills: comfortable with all phases of the data science development process, from initial analysis and model development to deployment
