Amazon Sr Software Dev Engineer AI Agent Identity 

United States, Washington, Seattle 

229373962

The Core Services team within AWS Applied AI Solutions is creating the foundations that will power the next generation of AI agents from small business to enterprise scale. As a technical leader, you'll lead our new agentic AI building blocks initiative, pioneering the development of reusable AI components that accelerate and standardize AI product delivery across AWS business applications such as contact center, supply chain, healthcare and life sciences. You'll own one critical capability area such as agent identity and governance, agent collaboration & orchestration, agent evaluation, or knowledge management, and have the privilege to define what we build and how we build it.This role combines the excitement of a startup environment with the scale of AWS. You'll research state-of-the-art open source and internal tools, tackle highly ambiguous problems, and lead a team building a V1 product from the ground up. You won't just be implementing someone else's vision — you'll chart the course, define the roadmap, and create solutions that eliminate non-differentiating work while ensuring enterprise-grade quality and consistency. If you thrive on ownership, are passionate about AI, and want to fundamentally influence how AWS builds AI products, this role offers an extraordinary opportunity to make your mark.
Key job responsibilities
- Own the technical architecture and strategy for a critical AI agent capability area, setting the foundation for enterprise-scale AI solutions across AWS- Research, evaluate, and integrate state-of-the-art AI technologies, making informed decisions about build vs. leverage approaches
- Design and implement reusable AI components that meet enterprise-grade quality standards while simplifying complex technical challenges- Champion engineering best practices, establishing a culture of robust software development with exemplary code organization, clarity, and maintainability- Communicate complex technical designs to diverse audiences, from engineers to non-technical stakeholders and senior leadershipA day in the life

- 5+ years of non-internship professional software development experience
- 5+ years of programming with at least one software programming language experience
- 5+ years of leading design or architecture (design patterns, reliability and scaling) of new and existing systems experience
- Experience as a mentor, tech lead or leading an engineering team
- Experience with full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations
- Experience designing and implementing AI/ML systems, including working with LLMs, prompt engineering, retrieval augmented generation (RAG), fine-tuning, or AI agent development
- Proven track record building distributed systems with well-designed APIs that operate reliably at enterprise scale
- Demonstrated ability to create reusable software components with clean interfaces that can be leveraged by multiple teams
- Strong working knowledge of AWS AI/ML services such as Amazon Bedrock, SageMaker, and related infrastructure
- Successful history of cross-organizational collaboration, driving technical convergence while maintaining delivery velocity

- 10+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience
- Bachelor's degree in computer science or equivalent
- Advanced identity management experience, including implementation of authentication systems for non-human entities, OAuth 2.0 token exchange protocols, and federated identity management frameworks
- Expertise in PII handling and data protection, with knowledge of data masking techniques, de-identification methodologies, and regulatory compliance frameworks for managing sensitive information in AI systems
- Experience designing sophisticated authorization frameworks featuring fine-grained permission models that support delegation, just-in-time approval workflows, and clear attribution between human and AI agent actions