Amazon.com Services LLC
Technology
Sr.AppliedScientist,AdsAICoreInfrastructure
Neural analysis suggests this role is
optimal for Senior candidates.
“Sr. Applied Scientist, Ads AI Core Infrastructure at Amazon.com Services LLC. Skills: Applied research, Machine learning, Agent orchestration, Data integration. Research and develop novel algorithms for agent-data interaction. Minimize latency, token consumption, and error rates”
What You'll Achieve.
Deliver accurate, trustworthy insights; Minimal latency and token consumption; Solutions constantly evaluating and improving; Sub-second latency
Industry & Context.
Root cause analysis; Troubleshooting; Data-driven decision making
What They're Looking For.
Must Have
3+ years of building machine learning models, Master's degree and 6+ years of applied research experience, Experience programming in Java, C++, Python or related language, Experience with neural deep learning methods, Experience with machine learning
Nice to Have
PhD, Experience with modeling tools such as R, scikit-learn, Spark MLLib, MxNet, Tensorflow, numpy, scipy etc., Experience with large scale distributed systems such as Hadoop, Spark etc.
What You'll Do.
Research and develop novel algorithms for agent-data interaction
Investigate multi-agent orchestration strategies
Develop techniques for automatic query optimization
Develop caching strategies based on agent behavior patterns
Invent new methods for compressing advertiser context representations
Preserve semantic meaning and analytical utility
Research optimal metadata generation techniques
Design evaluations to measure impact of data representations
Develop adaptive context selection algorithms
Pioneer new RAG-based embedding approaches
Optimize for real-time advertiser data delivery
Research and implement semantic search and retrieval techniques
Design advertiser context frameworks
Enable automatic schema mapping
Develop evaluation frameworks to measure performance
Design and execute rigorous experiments
Compare traditional API orchestration versus CodeAct patterns
Compare RAG-based approaches
Analyze large-scale advertiser interaction data
and optimization opportunities
Collaborate with engineering teams to productionize research innovations
Deploy innovations to 30+ advertising agents and skills
Establish evaluation metrics and benchmarks
Partner with agent builder teams
Understand data requirements and constraints
Work with platform engineers to implement MCP servers
Work with platform engineers to optimize data pipelines
Work with platform engineers to optimize sandbox execution
Collaborate with product managers to translate research insights
Translate research insights into product features
Translate research insights into roadmap priorities
Stay current on latest advancements in agentic AI
Author technical papers for top-tier conferences
File patents for novel techniques
Present research findings at internal tech talks
Present research findings at external conferences
Mentor engineers and junior scientists
How You'll Work.
Team & Collaboration
Cross-functional collaboration; Partner with agent builder teams; Work with platform engineers; Collaborate with product managers
Communication Scope
Technical papers; Research findings; Internal tech talks; External conferences
Full Job Description
Amazon Advertising is one of Amazon's fastest growing and most profitable businesses, responsible for defining and delivering AI-powered solutions that transform how advertisers make strategic decisions. We deliver billions of ad impressions and process massive volumes of advertiser data every single day. You'll work with us to pioneer breakthrough approaches in how AI agents access and reason over real-time advertiser data at scale. We are using generative AI and agentic systems to help advertising agents provide instant, strategic advice to millions of advertisers. You will need to invent new techniques for agent orchestration, context optimization, and code generation to ensure we're delivering accurate, trustworthy insights with minimal latency and token consumption. You'll create feedback loops to ensure our solutions are constantly evaluating themselves and improving. 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) servers—an 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. 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. Key job responsibilities Agent Orchestration & Optimization Research - Research and develop novel algorithms for agent-data interaction patterns that minimize latency, token consumption, and error rates - Investigate multi-agent orchestration st
Applying for this Sr. Applied Scientist, Ads AI Core Infrastructure role?
Most applicants get filtered before a human reads their resume. See if yours makes the cut.
ANONYMOUS · UNFILTERED
What do employees actually say about Amazon.com Services LLC?
Real rants from real employees. Read before you apply.