Amazon advertisers need better guidance and support for creating, optimizing, and growing their campaigns. The complexity of diverse advertiser goals, campaign types, and market dynamics creates a technical challenge where improvements in guidance systems can significantly impact advertiser success and the Amazon retail ecosystem. The company aims to build a personalized, context-aware agentic advertiser guidance system leveraging LLMs and various tools to address this.
Requirements
- Experience programming in Java, C++, Python or related language
- Experience in designing experiments and statistical analysis of results
- Experience in state-of-the-art deep learning models architecture design and deep learning training and optimization and model pruning
Responsibilities
- Design and build agents to guide advertisers in conversational and non-conversational experience.
- Design and implement advanced model and agent optimization techniques, including supervised fine-tuning, instruction tuning and preference optimization (e.g., DPO/IPO).
- Curate datasets and tools for MCP.
- Build evaluation pipelines for agent workflows, including automated benchmarks, multi-step reasoning tests, and safety guardrails.
- Develop agentic architectures (e.g., CoT, ToT, ReAct) that integrate planning, tool use, and long-horizon reasoning.
- Prototype and iterate on multi-agent orchestration frameworks and workflows.
- Collaborate with peers across engineering and product to bring scientific innovations into production.
Other
- PhD, or Master's degree and 4+ years of CS, CE, ML or related field experience
- 3+ years of building models for business application experience
- Experience in professional software development
- work safely and cooperatively with other employees, supervisors, and staff
- adhere to standards of excellence despite stressful conditions
