Senior Machine Learning Engineer, Payments & Risk

As a Senior Machine Learning Engineer at Gusto, your primary responsibilities include building and deploying machine learning models that identify, assess, and mitigate risks in the payments arena. You'll engage in comprehensive research to establish model requirements and partner with various teams to tackle complex cross-functional challenges.

Gusto seeks candidates with at least 8 years of experience in statistical analyses of large datasets and deep knowledge in machine learning. The ideal candidate would possess advanced degrees or equivalent experience in quantitative fields alongside proven capabilities in risk modeling, particularly in credit and fraud analysis.

In their role, a Senior Machine Learning Engineer plays a critical part in fulfilling Gusto's mission by leveraging data science to create model-driven solutions. By ensuring the safety and integrity of payment processes, you help empower small businesses and enhance their trust in our services.

Candidates for the Senior Machine Learning Engineer role should have strong programming skills in languages such as Python or R, capable of conducting everything from initial analyses to full model development and deployment. Familiarity with various statistical and modeling techniques like logistic regression and random forest is vital.

Gusto fosters a collaborative and inclusive work environment. As a Senior Machine Learning Engineer, you'll work in a team-oriented setting, both in the office and virtually, where communication and partnership with colleagues in engineering and product design are key to success.

In your response, highlight specific machine learning models you've worked on, particularly those that pertain to payment and fraud risk. Discuss the techniques used, the challenges faced, and how your contributions led to positive outcomes.

Discuss your systematic approach, starting from understanding the business problem and data collection, moving through feature engineering, model selection, training, and validation. Emphasize the importance of stakeholder communication throughout this process.

Detail your familiarity with various statistical techniques, such as regression analysis, hypothesis testing, or A/B testing. Provide examples of how you've successfully applied these methods in previous roles.

Explain your strategies for monitoring model performance, such as setting up performance metrics and regular retraining schedules, while also discussing the importance of stakeholder feedback in this process.

Share a specific instance where you presented statistical analysis results to a non-technical team. Focus on how you simplified complex concepts and ensured clarity while engaging your audience effectively.

Highlight your hands-on experience with programming in Python or R, detailing specific libraries and frameworks you’ve utilized for model development, analysis, or deployment, showcasing your technical proficiency.

Share details about a specific innovative project where you identified a risk management issue and developed a machine learning solution to address it, emphasizing its impact on overall operations or customer safety.

Talk about the resources you utilize to keep your skills sharp, whether through online courses, industry conferences, research papers, or community networking, showcasing your commitment to continuous learning.

Discuss potential challenges such as data quality, the evolving landscape of payment fraud, and regulatory compliance. Share how your experience has prepared you to navigate these challenges effectively.

Share your time management strategies, such as task prioritization, using project management tools, or collaborating with teams to reallocate resources as needed to meet deadlines without compromising quality.