Software Development Engineer — Production AI Agents (Harness)

Amazon Web Services (AWS); New York (NY); On-site; USD 158,000 - 214,000; Full time

Job summary

Amazon Development Center U.S., Inc. in New York seeks a Software Development Engineer to design, implement, test, and operate core components of the Harness control and data planes for Bedrock AgentCore.

You will work on distributed systems, agent orchestration, security, and low-latency streaming, collaborating across teams to deliver scalable, production-grade AI agent capabilities with configurable tools, memories, and templates.

Qualifications

• 3+ years of non‑internship professional software development experience.
• 2+ years of design/architecture experience of large systems.
• 1+ years in software development engineer roles.
• 1+ years designing large-scale distributed software applications.

Responsibilities

• Design, build, test, deploy, and operate high‑availability control plane APIs and data plane services.
• Build secure, isolated execution capabilities for tool orchestration, memory, streaming, identity, and networking.
• Develop integrations between Bedrock and third‑party models and customer environments.
• Implement versioning, endpoints, deployment, rollback, and evaluation features.
• Analyze latency, scalability, availability, and cost across multi‑tenant workloads.
• Simplify developer journeys across APIs, SDKs, CLI, and infrastructure as code.
• Engage with customers and partners to reduce friction and accelerate production.
• Contribute to architectural decisions and mentoring across teams.

Skills

Software development experience

Distributed systems

Operational excellence

Customer collaboration

Education

Bachelor's degree in CS/Engineering/Math

Tools

C#

C++

Java

Perl

Job description

Amazon Development Center U.S., Inc. in New York seeks a Software Development Engineer to design, implement, test, and operate core components of the Harness control and data planes for Bedrock AgentCore.

You will work on distributed systems, agent orchestration, security, and low-latency streaming, collaborating across teams to deliver scalable, production-grade AI agent capabilities with configurable tools, memories, and templates.