Applied Scientist, Amazon Data Engineering, Sciences and Analytics; DESA)

Amazon Live is building the future of shoppable video — connecting brands with customers through live streams, short-form video, and creator-driven content across Amazon Shopping, Fire TV, Prime Video, and social platforms. The product serves millions of monthly viewers, processes billions of events daily across 9 marketplaces, and generates tens of millions of dollars in advertiser revenue through self-service and managed channels with a goal to reach 100MM+ MAUs and 20K+ brands in the next couple of years.

Amazon Live has a mature data platform powering reporting across 9 marketplaces, 14+ dashboards, and real-time creator analytics. The opportunity ahead is different: proving the causal value of video to brands, Amazon's programmatic systems, and product decision-making. This requires production ML models, data experimentation frameworks, and content intelligence that do not exist today — and that is exactly what this role builds.

• Design and deploy causal attribution models (incrementality testing, multi-touch) replacing heuristic approaches, producing defensible numbers for partner teams and brand-facing ROI metrics.
• Build brand lifecycle models (LTV, cost-to-acquire, adoption funnel) and campaign optimization models (marketing mix, diminishing returns) that scale self-service revenue.
• Design and run A/B experiments with proper methodology (holdouts, pre-registration, power analysis) for new product surfaces, ranking changes, and attribution model transitions.
• Build multimodal and generative models for content intelligence — extracting structured signals from video and producing scored creative assets at scale.
• Develop ranking and personalization features (content affinity, creator quality indices, cross-session engagement patterns) consumed by downstream distribution systems.
• Build predictive models proving video value to Amazon's programmatic systems where existing retail signals fail.
• Own the full lifecycle from research question through production deployment, monitoring, and iteration.
• Present findings and methodology to senior leadership (Director/VP) and partner teams, translating model outputs into business decisions.
• Contribute to the science community through internal publications, reading groups, and cross-team methodology sharing.

We value builders who thrive in ambiguity, move fast from hypothesis to production, and measure their success by business outcomes rather than paper count.

You will partner directly with product managers, monetization leads, and engineering peers to scope what to measure and how to prove it. Some weeks you will be designing an incrementality framework for ad lift and presenting methodology to leadership. Other weeks you will be training a multimodal model on broadcast video, packaging ranking features for the distribution team, or developing an A/B experiment for a new video produce on a new discovery surface.

You will rapidly prototype and test hypotheses in a high-ambiguity environment, making use of both quantitative analysis and business judgment. You will work on DE-built foundational data assets (content metadata, shopper profiles, retail/advertising integrations) and have access to a self-serve analytics agents and agentic-operational tooling that accelerate exploration. You will present findings to senior leadership (Director/VP level) and partner teams, turning data into prioritization decisions.

The DESA team owns the data platform, analytics, and sciences for Amazon Live and Shop the Show. The team's mission: quantify the value of live video to Amazon's ecosystem and make that value programmable — for brands deciding where to invest, for product teams deciding what to build, and for Amazon's systems deciding what to show customers. You will be one of the first scientists on a team that has built the data foundation and is now ready to build the intelligence layer on top.

The platform processes event data from internal Amazon systems and social surfaces across 9 marketplaces. DEs own the infrastructure and foundational data assets. The BIE owns executive reporting. Applied Scientists own the…