Applied Scientist, Trust & Safety

About the Applied Science Team

We're looking for applied scientists with deep expertise in machine learning, optimization, building data products, and/or statistics. As part of a small product team you will have full ownership over your domain, so you should be a person who dreams big, then executes well.  

At Thumbtack, the Applied Science team is responsible for a wide variety of problems spanning machine learning, statistics, and computer science:

• Detect and prevent fraud to improve marketplace trust/safety for customers and pros. We play a critical role in maintaining a healthy and secure marketplace by leveraging ML to detect and prevent fraudulent activities and policy violations. Our work directly contributes to improving the experience for both customers and professionals by ensuring high-quality connections and safeguarding the platform.
• Improve customer and service provider matching. Matching and optimization algorithms are fundamental to Thumbtack’s product: we now service millions of matches per week. Identifying better matches between customers and service providers has an incredible impact on the experience of customers and professionals transacting on our platform.
• Model complex relationships in the presence of many confounding factors. Predictive modeling problems are everywhere across our product. Our team works to scope, design and implement machine learning models to support Thumbtack’s product and marketing.
• Characterize marketplace dynamics. Thumbtack’s marketplaces consist of thousands of active markets across our service categories and U.S. cities. Via exploratory data analysis and experimental design, our team works to understand trends and behaviors within these markets.
• Build a healthy marketplace. We evolve and manage the monetization mechanics of our marketplace, including defining the parameters that affect the prices we charge.
• Grow Thumbtack. We use various marketing and sales channels to drive traffic to Thumbtack. Leveraging causal inference and machine learning techniques, our team makes sure that we invest in sustainably growing Thumbtack.

Challenge 

Our team is at the forefront of a massive amount of user data related to interactions and activities on the Thumbtack platform. We need to think a lot about scaling our detection capabilities as well as how to provide robust security and trust for a wide set of users and scenarios. We are constantly working to improve our ability to identify and mitigate risks such as fraudulent accounts, spam messaging, and payment fraud, ensuring a safe and reliable experience for both sides of our Home Services marketplace. 

To this end, we are looking for someone with deep expertise in developing and deploying advanced machine learning (ML) models, including frontier AI and LLM models, to analyze various aspects of user and pro behavior, platform interactions and payment data to proactively address potential threats.

Responsibilities

• Initiate and drive applied science initiatives to completion with a focus on improving the trust and safety of the Thumbtack platform. This includes identifying opportunities to leverage machine learning to enhance spam and fraud detection, policy enforcement, and overall platform security. 
• Architect and deploy machine learning systems to production
• Design and execute experiments to evaluate the effectiveness of new models and strategies for improving trust and safety metrics such as reducing exposure to spam, detecting abuse and improving lead quality. 
• Analyze a wide variety of data: structured and unstructured, observational and experimental
• Collaborate with engineering, product, and operations teams to define problems, develop solutions, and ensure the successful implementation and monitoring of machine learning models for Trust & Safety.
• Maintain the right balance between speed of execution and scientific rigor when designing solutions
• Contribute to improving the overall performance of Trust & Safety models by exploring new features, algorithms, and data sources.

What you’ll need

If you don't think you meet all of the criteria below but still are interested in the job, please apply. Nobody checks every box, and we're looking for someone excited to join the team.

• Expert knowledge of machine learning techniques, including classification, anomaly detection, and natural language processing (NLP).
• Ability to effectively read, write, and debug code in programming languages such as Python
• Good knowledge of probability and statistics, including experimental design, optimization, and causal inference
• Demonstrated ability to create and drive technical and impactful roadmaps for the business, and lead seamless execution
• Ability to break down complex problems rigorously and understand the tradeoffs necessary to deliver impactful projects
• Ability to communicate clearly and effectively to cross functional partners of various technical levels

Bonus points if you have

• Experience in applied science in a Trust & Safety, security, or risk domain.
• Expert knowledge of probability and statistics, including experimental design, predictive modeling, optimization, and causal inference
• Experience in applied science in growth or marketing at a Marketplace
• Experience with large-scale distributed systems
• A Master’s or Ph.D. in a relevant field (e.g., Computer Science, Machine Learning, Statistics).

Thumbtack is a virtual-first company, meaning you can live and work from any one of our approved locations across the United States, Canada or the Philippines. Learn more about our virtual-first working model here. 

#LI-Remote