Design config-driven agent frameworks (tool-calling, action groups, investigation protocols) so new capabilities and metrics onboard without code changes
Develop debugging and log-traceability agents that trace an interaction end-to-end across every service component, so engineers debug in minutes instead of hunting logs per system
Architect agent authentication and token-propagation (e.g. user-identity / Midway into agent tool calls) that is secure by design
Inclusive Experience — Accessibility by Design
Develop accessibility features for AI experiences that work across diverse abilities, contexts, and modalities from the start rather than as an afterthought
Build the instrumentation that measures accessibility coverage and adoption so inclusive experiences are tracked like any other first-class metric
Create cross-device, multimodal interfaces (text, voice, visual) that preserve a consistent, inclusive experience across surfaces
Partner with UX and research to turn inclusive-design principles into shipped, measurable product capabilities
Key Technical Challenges
Automation vs. Accuracy: Drive operational burden down through AI automation while keeping leadership-facing metrics and root-cause output correct and trustworthy
Governance at Scale: Classify and control sensitive data across high scale volume without linear headcount growth, and prove compliance rather than assert it
End-to-End Observability: Trace interactions across many distributed service components with low latency, surfacing the right context for fast debugging
Multimodal & Inclusive Systems: Architect systems that handle text, voice, and visual inputs while delivering an accessible experience across modalities and devices
What Makes You Successful
Customer Obsession for Trust: You deeply understand that trust is earned through consistent, transparent, and privacy-respecting experiences. You make technical decisions that prioritize customer trust even when it means additional complexity.
Technical Excellence: You have strong computer science fundamentals and practical experience building distributed systems. You write clean, maintainable code and establish best practices that enable your team to move fast without breaking things.
AI & Privacy Expertise: You understand both the capabilities and limitations of modern AI systems. You know how to implement privacy-preserving techniques without sacrificing user experience.
Bias for Action: You thrive in ambiguous environments where you need to make pragmatic trade-offs between innovation and safety. You ship iteratively and learn from customer feedback.
Collaboration & Communication: You partner effectively with product managers, UX designers, data scientists, and other engineers. You can explain complex technical concepts to non-technical stakeholders and influence architectural decisions across teams.
Inclusive Mindset: You design systems that work for all customers, considering diverse abilities, contexts, and use cases from the start rather than as an afterthought.
Why Join Us
Work on generative AI technology that impacts millions of customers daily
Shape the future of responsible AI and set industry standards for privacy and trust
Partner with world-class product, design, and research teams
Solve novel technical challenges at the intersection of AI innovation and customer protection
Build systems that make AI accessible and trustworthy for everyone
A day in the life
You will be working with a group of talented engineers and scientists on running experiments to test scientific proposal/solutions to improve our trust-preserving experiences. This will involve collaboration with partner teams including engineering, PMs, data annotators, and other scientists to discuss data quality, policy, and model development. You work closely with partner teams across Alexa to deliver platform features that require cross-team leadership.
About the team
Who We Are
Trust CX Innovations is a strategic innovation team within Amazon Devices & Services that focuses on advancing AI technology while prioritizing customer trust and experience. Our team operates at the intersection of artificial intelligence, privacy engineering and customer-centric design.
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
5+ 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
Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace accommodation or adjustment during the application and hiring process, including support for the interview or onboarding process, please visit https://amazon.jobs/content/en/how-we-hire/accommodations for more information. If the country/region you’re applying in isn’t listed, please contact your Recruiting Partner.