Full Job Description
Build the agent execution engine powering autonomous advertising campaigns for 1.6 million advertisers - designing core infrastructure for LLM reasoning, multi-step orchestration, and reinforcement learning that enables agents to plan, reason, and act across complex advertiser workflows. Your contributions will form the backbone of the systems delivering personalized, context-aware guidance at massive scale.
The Autonomous Campaigns team within Sponsored Products and Brands is building a highly personalized campaign creation and management system that leverages LLMs together with auction simulations, ML models, and optimization algorithms. This agentic framework operates across both chat and non-chat experiences in the ad console - scaling from natural language queries to proactive guidance based on deep understanding of each advertiser. At our scale, even small improvements in guidance systems have outsized impact on advertiser success and Amazon's retail ecosystem. You'll work closely with senior engineers and applied scientists to translate research prototypes into robust, high-performance production systems - diving deep into LLM deployment frameworks, reinforcement learning infrastructure, and state-of-the-art agent architectures to solve real customer problems.
Key job responsibilities
- Implement core services and APIs for agent orchestration, tool invocation, and state management
- Build scalable, reusable data and tool registry systems that enable agents to reason across complex workflows
- Build components of evaluation pipelines (offline/online) for measuring reasoning quality, advertiser outcomes, and safety guardrails
- Develop infrastructure to support fine-tuning and reinforcement learning pipelines, collaborating with scientists to productionize workflows
- Ensure performance, scalability, observability, and maintainability through strong engineering practices
- Participate in system design, code reviews, and team architecture discussions
- Continuously learn and apply new techniques in agentic frameworks, distributed systems, and cloud-native development
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
- Experience programming with at least one software programming language
- Experience with AI/ML technologies
PREFERRED QUALIFICATIONS
- 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 equivalent
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 https://amazon.jobs/en/benefits.
USA, NY, New York - 158,100.00 - 213,800.00 USD annually
USA, WA, SEATTLE - 143,700.00 - 194,400.00 USD annually