Software Development Engineer- GENAI/ML, Amazon Catalog System Services(Level 5)

Join the Veritas team within Amazon's Selection and Catalog Systems (ASCS) organization as a Software Development Engineer focused on GENAI/ML initiatives. The team owns Amazon's premier LLM benchmarking and evaluation platform, critical for measuring and improving AI performance across the world's largest e-commerce product catalog.

In this role, you'll work directly with Large Language Models (LLMs) to enhance catalog data quality and customer experience at scale. You'll have extensive opportunities to work with in-house LLM hosting and inference systems, Amazon Bedrock, prompt tuning, and optimization techniques. As part of the team that evaluates AI performance across billions of products and attributes, you'll help build and leverage AI agents to assess LLM models, their applications, and the customer experiences they power.

Key responsibilities include:

• Developing distributed systems powered by LLMs and multi-modal ML models
• Building GenAI-driven solutions for evaluation quality and automation
• Designing AI-driven workflows for data enhancement
• Working with Amazon Bedrock and in-house LLM systems
• Creating comprehensive evaluation methodologies
• Partnering with scientists and AI experts

The Veritas team is a specialized, innovation-focused group within ASCS that owns Amazon's premier LLM evaluation and benchmarking platform. You'll work with cutting-edge generative AI technology while maintaining work-life balance and continuous learning opportunities. The role offers growth opportunities including leading industry-defining benchmarking standards for e-commerce AI and taking on leadership roles across Amazon's catalog ecosystem.

The ideal candidate brings experience in distributed systems, high-scale software services, and agile delivery practices. This position combines advanced generative AI development with large-scale distributed systems engineering, working on frameworks that teams across Amazon depend on for their AI development decisions.