Machine Learning Engineer, Fraud

About The Company

Whatnot is the leading live shopping platform in North America and Europe, revolutionizing the way people buy, sell, and discover their favorite items. As a dynamic and innovative company, Whatnot seamlessly blends community, entertainment, and commerce to create a unique online marketplace experience. With a presence in the US, UK, Germany, Ireland, and Poland, the company is committed to building the future of online marketplaces through cutting-edge technology and a passionate team. From fashion, beauty, and electronics to collectibles like trading cards, comic books, and live plants, Whatnot offers a diverse range of products through engaging live auctions. The company's mission is to enable anyone to turn their passion into a business and foster connections among users worldwide.

About The Role

We are seeking a talented and experienced Machine Learning Engineer to join our Trust & Safety team. In this role, you will be responsible for designing, training, and deploying both traditional machine learning models and large language models (LLMs) to detect and prevent fraudulent behaviors across our platform. You will lead the end-to-end architecture of fraud detection systems, ensuring a balance between platform security and a seamless user experience. Your work will involve building intelligent behavioral graphs, developing scalable data pipelines, and conducting deep behavioral analysis to identify emerging fraud tactics. Collaboration with cross-functional teams such as Payments, Infrastructure, and Trust & Safety is essential to develop effective features, labels, and evaluation pipelines. You will also implement model monitoring systems, contribute to fraud risk orchestration, and define key metrics to measure the effectiveness of detection systems. This role offers an exciting opportunity to work on innovative solutions that safeguard our marketplace while supporting our rapid growth and technological evolution.

Qualifications

Bachelor’s degree in Computer Science, Data Science, or a related field, or equivalent work experience
2–6 years of experience in machine learning or software engineering, preferably in risk, fraud, or trust & safety domains
Proficiency in Python and machine learning libraries such as scikit-learn, PyTorch, LightGBM
Solid backend development skills and experience deploying ML models in production environments (batch or real-time)
Experience with data analysis and building data pipelines using SQL, Spark, or DBT
Knowledge of fraud detection techniques, including chargeback prediction, anomaly detection, and graph-based modeling
Experience with data orchestration frameworks like Dagster or Kubeflow and feature store design
Ability to translate business risks into measurable ML solutions and collaborate across diverse teams

Responsibilities

Design, train, and deploy ML models and LLMs to identify fraudulent activities across user accounts, payments, and marketplace interactions
Lead the architecture of fraud detection, prevention, and intervention systems, ensuring a smooth user experience
Build and maintain behavioral graphs to model user patterns, collusion networks, and account connectivity
Develop scalable data pipelines and real-time inference systems to support high-volume, low-latency ML workloads
Conduct behavioral and adversarial data analysis to identify fraud trends and improve detection accuracy
Partner with cross-functional teams to develop features, labels, and model evaluation pipelines
Implement model monitoring, drift detection, and continuous improvement processes to maintain system reliability
Contribute to fraud risk orchestration by combining rules, heuristics, and models for automated decision-making
Define, track, and report key metrics such as precision, recall, false-positive rate, and latency to evaluate system performance
Stay informed about emerging fraud tactics and incorporate insights into adaptive, production-ready systems

Benefits

Generous holiday and time-off policies
Health insurance options including medical, dental, and vision coverage
Support for remote work with home office setup allowance
Monthly allowances for cell phone, internet, and wellness initiatives
Care benefits and annual childcare allowances
Lifetime family planning benefits covering adoption and fertility expenses
Retirement plans including 401(k) with employer matching and international pension options
Monthly app usage allowances for dogfooding
Paid parental leave of 16 weeks plus a gradual return to work
Opportunities for professional development and work-life balance in a flexible environment

Equal Opportunity

Whatnot is proud to be an Equal Opportunity Employer. We value diversity and are committed to creating an inclusive environment for all employees. We do not discriminate based on race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, parental status, disability, or any other protected characteristic. We believe that a diverse and inclusive workforce enhances our innovation, culture, and overall success. All qualified applicants will receive consideration for employment without regard to any protected status.