Applied Scientist, Minerva - Bengaluru | Amazon Job

Job Description

We are looking for Applied Scientists to advance how Minerva detects and responds to risk across KDP and Kindle Unlimited, building new models and raising the bar on the ones in production. You will own a problem end to end, from framing and modeling through evaluation and production launch, working with scientists and engineers in Bengaluru and the US.


Key job responsibilities
- Monitor production risk models and push their quality higher: track performance and drift, improve how performance is measured, and lead the deep-dive science that turns model behavior into better detection.
- Design, train, and evaluate improved detection models, and take them to production with engineering partners.
- Build datasets, labels, evaluation sets, and metrics, and strengthen them as abuse patterns change.
- Write clear readouts with recommendations for scientists, engineers, and policy partners.

About the team
Kindle Direct Publishing (KDP) has empowered a new wave of self-motivated creators, tearing down barriers that once blocked writers from reaching readers. Minerva is the science and analytics organization for Amazon's Books business. We build systems for content understanding, author marketing and discovery, fraud and abuse prevention, and content risk, and we optimize manufacturing, fulfillment, and quality for Print On Demand (POD). We have mature areas and green-field opportunities, with engineering, business intelligence, and data engineering support across our areas. We are now building science teams in Bengaluru that work closely with our scientists in the US. Risk Science, a team within Minerva, keeps fraud, abuse, copyright infringement, and harmful content out of the Books catalog and programs such as Kindle Unlimited, using text, image, and behavioral data.

Basic Qualifications:

- 3+ years of building models for business application experience
- PhD, or a Master's degree and experience in CS, CE, ML or related field research
- Experience in any of the following areas: algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing
- Experience programming in Java, C++, Python or related language

Preferred Qualifications:

- Experience in patents or publications at top-tier peer-reviewed conferences or journals
- Experience with fraud detection, abuse prevention, trust and safety, or content moderation
- Experience with model monitoring, data drift detection, or calibration
- Experience with graph-based ML, behavioral modeling, or anomaly detection
- Experience with large-scale data processing (for example Spark or SQL on large datasets)
- Demonstrated experience leveraging generative AI tools to enhance workflow efficiency and productivity, with the ability to craft effective prompts and critically evaluate AI-generated outputs in a professional setting