Senior Applied Scientist, Amazon Ads, Demand Tech , Amazon Advertising, Demand Tech

In Amazon Advertising, we apply Machine Learning at massive scale to optimize programmatic advertising performance. The Demand Tech team owns response prediction and incrementality models that power bid optimization across Amazon DSP and Sponsored Display - determining how billions of ad impressions are valued and served daily across Amazon-owned properties, the open internet, and third-party exchanges.

We are looking for a talented Senior Applied Scientist to join our team of scientists and engineers working on high-impact prediction systems that directly drive advertiser KPIs (CPA, ROAS, incrementality) across endemic and non-endemic programmatic advertising.

What you will do:

Own end-to-end response prediction - design and improve deep learning models for multi-task prediction (click, conversion, page view, incrementality) serving at inference latencies under 10ms at millions of TPS

Build and iterate on calibration mechanisms that keep prediction accuracy stable across rapidly shifting supply distributions

Integrate novel signals (OpenRTB features, customer behavioral sequences, supply quality feeds) into production models to improve optimization quality

Run online A/B experiments at scale, analyze results with statistical rigor, and translate offline gains into measurable business impact

Collaborate closely with engineers on model serving infrastructure (SageMaker, GPU inference, real-time feature stores) to deploy models efficiently at scale

Mentor scientists on the team and contribute to the broader Amazon ML science community through papers, conferences, and internal deep dives

What makes this role unique:

Direct business impact: Your models determine bid prices for billions of daily ad impressions - a 1% prediction improvement translates to tens of millions in advertiser value

Technical depth at scale: Multi-task deep learning architectures serving real-time inference across multiple global regions under strict latency constraints

Diverse problem space: From signal-sparse open internet prediction to calibration under distribution shift, from incrementality measurement to cost-efficient GPU inference

Autonomy and ownership: End-to-end ownership from problem framing through research, experimentation, production deployment, and business metric monitoring

Impact and career growth:

Amazon is investing heavily in building a world-class advertising business. Your work directly influences how Amazon"s advertising products optimize campaign performance for advertisers worldwide. You will work with a highly motivated, collaborative team with a broad mandate to experiment and innovate. You will have opportunities to present to senior leadership, define long-term science vision, attend external conferences (NeurIPS, KDD, ICML), and shape the direction of ML-driven advertising at Amazon.