Applied Scientist - II

Job description
The Ads Real-Time Data Service team is seeking an exceptional Applied Scientist to research and develop novel approaches for agent-data interaction. The Ads Real-Time Data Service team is solving one of the most critical challenges in advertising AI: instant access to advertiser context. We're building the infrastructure that provides immediate, pre-computed access to advertiser data via Model Context Protocol (MCP) serversan emerging standard for AI agent-data interaction. We're building summarized data for context using a mix of state of the art techniques like CodeAct and RAG-based embeddings, achieving a fundamental transformation in how AI agents interact with data.

We value technical excellence, customer obsession, and sustainable engineering practices. Our team includes engineers with diverse backgrounds in distributed systems, real-time data processing, AI/ML infrastructure, and platform engineering. We celebrate innovation (patent submissions encouraged), knowledge sharing (weekly tech talks), and continuous learning. We maintain a sustainable pace with minimal on-call burden, flexible work arrangements, and a strong focus on work-life balance. We're at the forefront of AI-assisted development, using tools like Kiro to accelerate our development cycles from weeks to days.

This role balances applied research (60%) with productionization (40%), giving you the opportunity to both advance the state of the art and see your innovations deployed at Amazon scale.

The core responsibilities for the job are as follows:

Agent Orchestration and Optimization Research:
• Research and develop novel algorithms for agent-data interaction patterns that minimize latency, token consumption, and error rates
• Design and implement CodeAct pattern variations enabling agents to write and execute analytical code in isolated sandboxes
• Investigate multi-agent orchestration strategies for complex advertiser queries requiring data from multiple sources
• Develop techniques for automatic query optimization and caching strategies based on agent behavior patterns

Large Language Model Context and Token Optimization:
• Invent new methods for compressing advertiser context representations while preserving semantic meaning and analytical utility
• Research optimal metadata generation techniques that help large language models understand and reason over structured advertiser data
• Design experiments to measure the impact of different data representations on agent response quality and token efficiency
• Develop adaptive context selection algorithms that dynamically choose relevant data based on query intent

RAG-Based Embeddings and Semantic Search:
• Pioneer new RAG-based embedding approaches optimized for real-time advertiser data delivery with sub-second latency
• Research and implement semantic search and retrieval techniques for advertiser datasets using vector embeddings
• Design advertiser context frameworks that enable automatic schema mapping from advertiser concepts to data representations
• Develop evaluation frameworks to measure performance across dimensions of latency, accuracy, and developer experience

Experimentation and Productionization:
• Design and execute rigorous experiments comparing traditional API orchestration versus CodeAct patterns and RAG-based approaches across metrics like success rate, latency, token consumption, and response quality
• Analyze large-scale advertiser interaction data to identify patterns, bottlenecks, and optimization opportunities
• Collaborate with engineering teams to productionize research innovations and deploy them to advertising agents and skills
• Establish evaluation metrics and benchmarks for agent-data interaction performance

Basic qualifications:
• 3+ years of building models for business applications experience.
• PhD, or Master's degree and 4+ years of CS, CE, ML or related field experience.
• Experience in patents or publications at top-tier peer-reviewed conferences or journals.
• Experience programming in Java, C++, Python or related language.
• Experience in any of the following areas: algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing.

Preferred qualifications:
• Experience using Unix/Linux.
• Experience in professional software development.