Data Scientist, Special Projects & Investigations
DESCRIPTION
The Customer Trust (CT) mission is to keep Amazon stores safe and trustworthy for our buyers, brands and selling partners, by enabling our selling partners to provide great CX while ensuring bad actors are kept out of our stores. The Selling Partner Risk (SPR) team within CT designs and implements policies, tools and technology innovations to protect customers by identifying and preventing abuse worldwide. Our growth requires highly skilled candidates who move fast, have an entrepreneurial spirit to create new solutions, a tenacity to get things done, thrive in an environment of ambiguity and change, and are capable of breaking down and solving complex problems. We value individual expression, respect different opinions, and work together to create a culture where each of us is able to contribute fully. Our unique backgrounds and perspectives strengthen our ability to achieve Amazon's mission of being Earth's most customer-centric company.
We catch bad actors and stop online fraud. It’s fun. It’s hard. It matters. We are passionate about protecting our selling partners and customers from bad actors and want a candidate that shares that passion. Amazon is one of the world’s most trusted companies. Help us keep it that way.
To achieve this, we are looking for an experienced data scientist with a background in risk, digital fraud, or cybersecurity. The data scientist will be responsible for developing and maturing a proactive abuse detection capability for the organization. This will include systematically evaluating investigator insights, heuristic rules, intelligence data, and model scores to identify predictors of malicious seller behavior and to operationalize them through new machine learning models. Familiarity with large language models is preferred.
The ideal candidate should be passionate about use of advanced data analytics and technology approaches to identify patterns and establish connections to uncover process and technology gaps and prevent fraud across Amazon stores worldwide. Your decisions are not only fundamental to helping protect customers and selling partners but will help maintain the health of Amazon’s catalog and product listings ecosystem.
Key job responsibilities
- Develop models to detect clusters or anomalies within unknown or poorly understood populations
- Evaluate, synthesize, and operationalize risk signals, machine learning models, and expert feedback for high-impact enforcement decisions
- Work closely with industry specialists to support critical and high impact projects while generalizing and scaling investigation findings
- Propose and champion large language model-based solutions to scale manual fraud detection processes
- Partner with data scientists, ML experts, and engineers and on cross-disciplinary efforts with other scientists within Amazon
About the team
Our team is comprised of specialists from many different backgrounds primarily focused around risk management, fraud, and information security. We leverage our individual strengths to solve large enduring problems through data that require long-term focus and ownership. We uncover the root cause of these problems by constantly identifying changes in behavior and new patterns or trends that deviate from the norm. We work quickly and can pivot to address new emerging threats. We enjoy the challenge of investigating the unknown areas of fraud and abuse and support multiple partner teams in raising the bar to improve detection and proactively find bad actors across our stores.
BASIC QUALIFICATIONS
- 2+ years of data scientist experience
- 3+ years of data querying languages (e.g. SQL), scripting languages (e.g. Python) or statistical/mathematical software (e.g. R, SAS, Matlab, etc.) experience
- 3+ years of machine learning/statistical modeling data analysis tools and techniques, and parameters that affect their performance experience
- Experience applying theoretical models in an applied environment
PREFERRED QUALIFICATIONS
- Experience in Python, Perl, or another scripting language
- Experience in a ML or data scientist role with a large technology company
Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.