Job Information
Amazon System Development Engineer I in Bengaluru, India
Description
Are you interested in building high-performance, globally scalable automation solutions — including AI-driven agentic workflows — that support Amazon Ads' current and future growth? Are you seeking an environment where you can drive innovation by leveraging the scalability and breadth of Amazon's AWS cloud services and cutting-edge generative AI capabilities? Do you have a passion for eliminating manual toil, enabling intelligent decision-making, and ensuring a seamless internal customer experience? This is the job for you.
The Amazon Ads Technology Team is looking for a results-oriented, driven Automation Developer who can help us design, build, and maintain the next generation of intelligent automation solutions — spanning traditional Robotic Process Automation (RPA), scripted workflow orchestration, and Agentic Process Automation (APA) powered by large language models (LLMs) and AI agents. Our ideal candidate thrives in a fast-paced environment, enjoys the challenge of highly complex business contexts that are often being defined in real-time, and is energized by the opportunity to push the boundaries of what automation can achieve — from rule-based task execution to autonomous, context-aware AI agents that reason, plan, and act.
As an Automation Developer on the Amazon Ads team, you will work on real-world problems at global scale, own your systems end to end, and influence the direction of technology that powers one of Amazon's fastest-growing businesses. You can expect to design flexible and scalable automation frameworks — including agentic architectures where AI agents autonomously orchestrate multi-step workflows, make decisions, invoke tools, and collaborate with other agents or humans in the loop — and work on some of the most complex challenges in large-scale intelligent process automation. Coming to Amazon Ads gives you the opportunity to work on a focused development team in a rapidly growing organization that directly impacts advertisers, partners, and customers worldwide.
You will design, implement, and test highly scalable automation solutions using AWS cloud platform services (Lambda, Step Functions, Bedrock, SageMaker, etc.), internal Amazon automation frameworks, Python, LLM-based agent frameworks, and other orchestration tools in challenging agile projects, working alongside best-in-class professionals.
In this role you will:
Deliver a best-in-class internal customer experience by continuously improving the automation platform, code, and services that enable Amazon Ads operations globally.
Design and develop robust integration patterns for our automation ecosystem. Leverage and integrate with different tools, technologies, and products within Amazon (e.g., internal RPA platforms, AWS Step Functions, Lambda, S3, CDK, Amazon Bedrock) to reduce operational cost and enhance the customer experience.
Architect and build Agentic Process Automation (APA) solutions where AI agents can:Autonomously understand and decompose complex, multi-step business processes.
Reason about context, make decisions, and determine the optimal sequence of actions.
Invoke APIs, tools, databases, and other systems as needed to complete tasks.
Handle exceptions intelligently — escalating to human-in-the-loop review when confidence is low or business rules require it.
Collaborate with other agents in multi-agent architectures for end-to-end process orchestration.
Partner directly with Software Development Engineers (SDEs), Applied Scientists, Technical Program Managers, Business Intelligence Engineers, Functional Analysts, and business stakeholders to understand workflows and continuously identify opportunities to build and deploy automation solutions — from deterministic RPA to intelligent agentic workflows.
Analyze existing manual and semi-automated processes, document current-state workflows, perform gap analysis, and propose automation strategies that maximize impact — recommending where traditional automation is sufficient and where agentic AI can unlock step-change improvements.
Build, maintain, and monitor automation pipelines and AI agent workflows with appropriate logging, alerting, guardrails, error handling, and retry mechanisms to ensure high reliability and responsible AI practices.
Design evaluation and feedback loops for agentic systems — including accuracy metrics, human review workflows, agent performance dashboards, and continuous improvement mechanisms.
Champion engineering best practices including code reviews, unit/integration testing, CI/CD, prompt engineering standards, agent testing strategies, and documentation standards within the automation team.
Contribute to the migration of existing third-party (3P) automation solutions to internal Amazon platforms, driving cost savings and operational excellence — and identify opportunities to upgrade legacy rule-based automations to intelligent agentic solutions where appropriate.
Stay current with the rapidly evolving landscape of agentic AI, LLM-based tool use, agent frameworks (e.g., LangChain, LangGraph, Amazon Bedrock Agents, AutoGen, CrewAI), and apply emerging best practices to our platform.
Basic Qualifications
Bachelor's degree in Computer Science, Software Engineering, Information Systems, or a related field (or equivalent professional experience).
3+ years of experience building and delivering automation solutions (RPA, scripted process automation, or workflow orchestration).
Proficiency in at least one programming/scripting language: Python, Java, or TypeScript.
Experience building complex software or automation systems that have been successfully delivered to customers/stakeholders.
Solid understanding of software development lifecycle practices including version control (Git), code review, testing, and CI/CD.
Preferred Qualifications
Experience with AWS services such as Lambda, Step Functions, S3, DynamoDB, CloudWatch, CDK, Amazon Bedrock, Amazon Bedrock Agents, SageMaker, or similar cloud-native tooling.
Hands-on experience with agentic AI / LLM-based automation, including:Building AI agents that use tools, APIs, and external systems to complete tasks autonomously.
Working with agent orchestration frameworks (e.g., LangChain, LangGraph, Amazon Bedrock Agents, AutoGen, CrewAI, Semantic Kernel, or similar).
Designing prompt chains, system prompts, and agent instructions for reliable, production-grade behavior.
Implementing guardrails, human-in-the-loop patterns, and evaluation frameworks for agentic systems.
Experience with RPA platforms (e.g., UiPath, Automation Anywhere, Blueprism, PEGA or internal Amazon automation frameworks) and a track record of migrating automations across platforms.
4+ years of experience building test automation frameworks and tools.
Experience in a test-driven and formal QA development environment, including development, staging, and production (or equivalent) deployment cycles.
Familiarity with Ads technology ecosystems, ad-serving platforms, or digital advertising operations.
Experience with data querying (SQL) and working with large-scale datasets for process analysis.
Understanding of responsible AI principles — including bias mitigation, transparency, and safety considerations for autonomous systems.
Strong written and verbal communication skills; ability to create clear technical documentation and present to both technical and non-technical audiences.
Key job responsibilities
Interact with business customers and Ads operations teams to understand, document, and prioritize their business processes and automation requirements.
Perform gap analysis to determine the optimal automation approach — rule-based RPA, scripted automation, API integration, agentic AI, or a hybrid — for each use case.
Design, code, test, and deploy automation solutions (including AI agent workflows) following Amazon's engineering and responsible AI standards.
Build and maintain agent orchestration layers that manage agent planning, tool selection, memory/context management, and human-in-the-loop escalation.
Work with business customers, developers, applied scientists, and partner teams to troubleshoot, document, and resolve system issues.
Define and track key metrics (hours saved, error rates, SLA adherence, agent accuracy, human escalation rates) to measure automation impact and continuously improve.
Participate in on-call rotations to support production automation and agent workflows as needed.
Basic Qualifications
Experience programming with at least one modern language such as Python, Ruby, Golang, Java, C++, C#, Rust
Experience in automating, deploying, and supporting infrastructure
Preferred Qualifications
- Experience with CI/CD pipelines build processes
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 https://amazon.jobs/content/en/how-we-hire/accommodations for more information. If the country/region you’re applying in isn’t listed, please contact your Recruiting Partner.