Software Development Engineer, AI Ops Integration
Search Jobs
Search by job, company or skills
Search by job, company or skills
As part of Ops AI Integration, we partner with RoW APEX AI Strategy & Implementation to build impactful AI solutions for Amazon's global operations customers. We are building an AI platform (MCP tools, multi-agent orchestration and AI Hub interfaces) and delivering critical solutions for RoW Operations within transportation and fulfillment.
As a Senior Software Development Engineer, you'll own the architecture and delivery of production systems that combine LLM-powered automation, multi-agent orchestration, and scalable platform infrastructure. You'll build solutions that automate carrier management, evolve our AI platform (MCP tools, AI Hub, shared modules), and deliver AI experiments. You'll also shape the development-as-a-service tech stack that enables our Forward Deployed Builders Program: setting engineering standards that scale AI builders across geographies.
This role combines startup-level ownership with Amazon-scale impact. You'll tackle highly ambiguous problems, contribute to shared architecture decisions across overlapping use cases, and directly influence how Amazon Operations leverages AI globally. If you thrive on end-to-end ownership, want to ship AI systems that have real business impact, and want to build the platform that hundreds of builders deploy on, this is the role for you.
Key job responsibilities
. Lead the technical design and architecture of production AI systems end-to-end, from data pipelines and model serving to scalable, user-facing applications across RoW transportation and fulfillment
. Architect and build multi-agent orchestration solutions (e.g. MCP tools, AI Hub modules) that automate complex operational workflows across multiple systems, APIs, and decision points
. Own and evolve the Synapse AI platform, designing shared infrastructure, reusable components, and interfaces that serve non-technical operations users across multiple geographies
. Define the integration architecture across internal systems, databases, and MCP servers, establishing patterns that enable modular, scalable orchestration adopted worldwide
. Shape the development-as-a-service tech stack for the Forward Deployed Builders Program, setting engineering standards, templates, and tooling that scale AI builders across regions
. Drive engineering excellence across the ML lifecycle: set standards for experimentation, deployment, monitoring, evaluation, and incident response
. Design guardrails, evaluation frameworks, and human-in-the-loop architectures that ensure production AI systems operate safely and reliably at scale
. Partner with scientists, product managers, and operations leaders to translate ambiguous business problems into well-scoped technical solutions with clear delivery milestones
About the team
We're a cross-functional team of machine learning engineers, ML & AI scientists and Technical PM focused on automating operational decisions in Amazon's supply chain.
Our charter is to identify high-impact automation opportunities, build AI agents that can handle them reliably, and deploy these systems into production
where they process real decisions daily.
The team operates with a build-measure-learn cycle. We work closely with operations partners to understand their problems, prototype solutions quickly, measure impact rigorously, and iterate based on real-world performance.
- Bachelor's degree
- Experience as a mentor, tech lead or leading an engineering team
- Experience leading the architecture and design (architecture, design patterns, reliability and scaling) of new and current systems
- Experience programming with at least one modern language such as Java, C++, or C# including object-oriented design
- Knowledge of Machine Learning and LLM fundamentals, including transformer architecture, training/inference lifecycles, and optimization techniques
- Experience scripting in Python or Javascript
- Demonstrated ability to rapidly prototype and iterate using AI-assisted development (vibe coding), leveraging LLMs and generative tools to compress weeks of engineering effort into days and multiply output across teams
- Master's degree in computer science or equivalent
- Experience with full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations
- Knowledge of system performance, memory management, and parallel computing principles
- Experience building complex software systems that have been successfully delivered to customers
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 for more information. If the country/region you're applying in isn't listed, please contact your Recruiting Partner.
Job ID: 152203303
Skills:
Performance Testing, Design Patterns, Concurrent Programming, Idempotence, eventual consistency, language framework, security scanning, programming languages paradigms, IDE language and toolset, abstraction layer, CQRS
Skills:
bedrock , Angularjs, Pl Sql, HTML, Javascript, Docker, Terraform, Gitlab, Java, CSS, Cloudformation, J2EE, Sql, Oracle Rdbms, Kubernetes, Spring Framework, Claude, Amazon SageMaker, RESTful service development, DevOps concepts, Kiro, AI ML capabilities, AgentCore, AWS Cloud Services, GitHub Copilot
Skills:
Software Development, Ux Design, Software Programming
Skills:
Java, Design Patterns, AWS, full-stack development
Skills:
Java, Git, REST, Graphql, Javascript, Python, Api Testing
