Senior SDE: Agentic Systems for AI Documentation

Amazon Web Services (AWS); New York (NY); Presencial; USD 185.000 - 250.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Health insurance

401(k) matching

Paid time off

Parental leave

Descripción de la vacante

Amazon Development Center U.S., Inc. in New York seeks a senior software engineer to own the architecture behind AWS Documentation's AI-powered workflows.

You will run a runtime that executes documentation workflows autonomously and orchestrate multi-agent authoring tools that transform design documents into service model content. You’ll define how agents divide work, evaluate output, and decide when human review is needed, balancing latency, cost, and correctness in a fast-changing AI domain.

Formación

• 5+ years of non-internship professional software development experience.
• 5+ years programming in at least one software language.
• 5+ years leading design or architecture of systems.
• Experience mentoring or leading an engineering team.

Responsabilidades

• Own architecture across the portfolio: agent runtime, multi-agent workflows, analyzers, telemetry.
• Define correctness and verifiability: ground output in sources and flag fabrication.
• Lead cross-team projects including orchestration patterns and developer tools.
• Turn quality evaluations into feedback to improve agent behavior and reliability.
• Raise engineering standards through reviews and mentoring while balancing speed.

Conocimientos

Software development

Programming experience

Design/architecture leadership

Mentor / tech lead

Educación

Master's degree in computer science or equivalent

Descripción del empleo

Amazon Development Center U.S., Inc. in New York seeks a senior software engineer to own the architecture behind AWS Documentation's AI-powered workflows.

You will run a runtime that executes documentation workflows autonomously and orchestrate multi-agent authoring tools that transform design documents into service model content. You’ll define how agents divide work, evaluate output, and decide when human review is needed, balancing latency, cost, and correctness in a fast-changing AI domain.