Software Development Engineer, Ads AI Core Infrastructure (ACI), Ads AI Core Infrastructure

At Amazon Ads, we're re-imagining the advertising landscape through advanced generative AI technologies and AI agents, revolutionizing how millions of customers discover products and engage with brands online. We are at the forefront of re-inventing advertising experiences, bridging human creativity with artificial intelligence to transform every aspect of the advertising lifecycle — from ad creation and optimization to performance analysis and customer insights.The Ads Agent Fabric team delivers the AI infrastructure platform that accelerates agentic application development from months to weeks. We build the agent-builder SDK with pre-integrated Ads features, developer tools that accelerate the develop, test, and model evaluation lifecycle, and a fully-managed stateful runtime with integrated access to Ads services, data, and foundational models. Our platform solves core production challenges: managing execution state across multi-step reasoning and multi-agent orchestration, enabling resumability through checkpointing and task queues for long-running workflows, and providing memory primitives that enable stateful experiences where agents remember and learn across sessions.You will build Tier-1 services to handle millions of requests per day, while maintaining response latencies in the milliseconds and meeting strict SLA requirements. You will develop distributed solutions with service-oriented architecture to build high-performance platforms powering the next generation of AI-driven advertising experiences. Our systems and algorithms operate on massive datasets using distributed frameworks. In this role, you will design new and rebuild existing solutions for the fast-growing scale of agentic infrastructure — including stateful runtime services, and pre-built platform components that agent-builder teams rely on to ship production agents.You will not merely go through the full software development cycle but more importantly drive appropriate technology choices for the business, lead the way for continuous innovation, and shape the future of AI-powered advertising at Amazon.We are a highly motivated, collaborative, and fun-loving team building at the forefront of AI agent infrastructure. We are entrepreneurial and have a bias for action with a broad mandate to experiment and innovate. This is an opportunity to make a significant impact on the future of AI agents in the Amazon Advertising business.A successful candidate will have the satisfaction of seeing their work power thousands of AI agents serving millions of advertisers globally, broaden their technical skills across distributed systems and ML infrastructure, and work in an environment that thrives on creativity, experimentation, and product innovation.Key job responsibilitiesSDE-2s are autonomous contributors to their team's software. You deliver working features spanning the full software lifecycle including working backwards from customers, software design, implementation, testing, deployment, operations, and documentation.SDE-2s coach others on producing high-quality code, using processes such as code review as a teaching mechanism. They ensure that when their software fails, the root cause is identified and eliminated with a permanent fix. They ensure the software they produce can be maintained and extended by those not familiar with the code by writing clear documentation and making good design choices.SDE-2s participate in an inclusive, constructive dialogue with other team members and members of closely related teams. They train new team members on how their software is constructed, how it operates, and how it fits into the bigger picture.About the teamAgent Fabric is Amazon Ads' AI infrastructure platform. We extend AWS AgentCore with advertising-specific capabilities and a managed, stateful runtime, cutting agent development from months to weeks. We own the platform end-to-end: the agent-builder SDK, the runtime that executes agents in production, and the knowledge and governance layers that keep it safe and accountable at scale. Our systems are in the critical path for GenAI projects across Amazon Advertising.Stateful Runtime & Orchestration: an orchestration framework that turns a single agent turn into durable, resumable work: async conversations that persist after a turn ends and notify on completion, scheduled and event-driven workflows, and multi-step DAG execution with fan-out, cancellation, and retry. Checkpointing, task queues, and short- and long-term memory let agents resume and learn across sessions.Knowledge Base: the RAG Knowledge Base that grounds advertiser answers across Sponsored Products, Sponsored Brands, DSP, reporting, and optimization. We run the KB agent, an OpenSearch vector index, and a daily ingestion pipeline spanning published and partner-curated content, with eval gates that enforce retrieval quality before every rebuild.Pre-Built Ads Components: delegated advertiser authorization, privacy-safe logging, policy guardrails, real-time data access, and context handoff between agents.Metering & Throttling: metering every invocation across model calls, tool calls, memory operations, and session time, then enforcing per-user and per-advertiser limits on a sub-millisecond path to protect the platform from abuse.Operational Excellence: parallelization for low latency, human-in-the-loop approvals, end-to-end tracing, security isolation, cost attribution, and versioned deploys with rollback.Basic qualifications- 3+ years of non-internship professional software development experience- 2+ years of non-internship design or architecture (design patterns, reliability and scaling) of new and existing systems experience- 1+ years of software development engineer or related occupational experience- 1+ years of designing and developing large-scale, multi-tiered, multi-threaded, embedded or distributed software applications, tools, systems, and services using: C#, C++, Java, or Perl experience- 1+ years of Object Oriented Design experience- Bachelor's degree or foreign equivalent in Computer Science, Engineering, Mathematics, or a related field- Experience programming with at least one software programming languagePreferred qualification - 3+ 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 equivalentAmazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status.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.The base salary range for this position is listed below. Your Amazon package will include sign-on payments and restricted stock units (RSUs). Final compensation will be determined based on factors including experience, qualifications, and location. Amazon also offers comprehensive benefits including health insurance (medical, dental, vision, prescription, Basic Life & AD&D insurance and option for Supplemental life plans, EAP, Mental Health Support, Medical Advice Line, Flexible Spending Accounts, Adoption and Surrogacy Reimbursement coverage), 401(k) matching, paid time off, and parental leave. Learn more about our benefits at .USA, NY, New York - 158,100.00 - 213,800.00 USD annually