SysDev Eng, OTS - Data ANCHOR Team

Are you a builder who gets energized turning ideas into production systems? Do you want to build AI-powered agents and data-driven solutions that solve real-world operational problems at Amazon's global scale? If working with GenAI, data infrastructure, streaming APIs, and shipping solutions fast excites you - this role is for you., Amazon's Ops Tech Solutions (OTS) Data ANCHOR organization is seeking a Systems Development Engineer with a software development background and passion for AI/data systems to join our Decision Intelligence team. You will build and ship agentic AI solutions and AI-enabled data infrastructure that integrates with third-party platforms (ServiceNow, APM etc,), first-party Amazon systems, and cross-organizational services spanning OTS and Reliability Maintenance Engineering (RME).

You will take designs and POCs and turn them into production-grade agents, MCPs (Model Context Protocols), and data-driven automation systems that drive measurable impact across Amazon's worldwide operations. A critical part of this role is ensuring our AI agents are backed by robust, well-architected data pipelines - building the streaming connections, APIs, and data integrations that make agents intelligent and analytical tools prescriptive. You'll own the development of Data MCPs and Analytical MCPs that power self-service data access and AI-ready infrastructure for our team and partners.

You'll work alongside senior engineers, data scientists, and data engineers - learning business processes directly from the field and translating them into intelligent, data-backed automation that supports technicians and engineers globally., Build and maintain agentic AI solutions - implementing agent orchestration logic, API integrations with ServiceNow (3P), and Amazon internal systems (1P)

• Develop Data MCPs and Analytical MCPs that enable AI agents and partners to consume, query, and act on operational data effectively
• Build and maintain streaming data connections and APIs that feed AI agents with real-time, high-quality data inputs
• Partner with Data Scientists and Data Engineers to implement AI-ready data pipelines, ensure data quality, and develop agent capabilities (LLM tool-use, prompt templates, RAG patterns)
• Translate POCs into production-ready systems with high code quality - writing tests, documentation, and monitoring from day one

Data Architecture & System Integration

• Architect and build AI-enabled data infrastructure that ensures agents and analytical tools have reliable, governed, and performant access to data
• Build integrations across OTS and RME ecosystems, connecting agents to upstream/downstream data sources, streaming platforms, and enterprise services
• Ensure data readiness for AI - designing schemas, data contracts, and pipeline patterns that make data consumable by agents and ML models at scale
• Implement user-facing platform features and dashboards where AI integrations and analytical MCPs surface prescriptive recommendations to field partners
• Contribute to guardrails, evaluation mechanisms, and data quality checks for production AI systems

Engineering Excellence & Operational Ownership

• Write clean, well-tested, production-quality code and participate in code reviews
• Own features end-to-end - from implementation through CI/CD deployment to production monitoring
• Participate in on-call rotations and drive operational excellence for production agents and data pipelines
• Deploy long-term scalable solutions - not throwaway prototypes - with observability, alerting, and production-readiness standards

A day in the life This role partners with data and systems organizations across OTS to build automations, data solutions, and agentic AI tools that provide a prescriptive mindset for our field operations, IT, and maintenance partners. You'll work with data streaming solutions, APIs, and data teams to build production-grade systems backed by AI and robust data integration processes.

On any given day, you might be building a streaming data pipeline that feeds an AI agent's decision engine, developing an Analytical MCP that gives partners self-service access to operational insights, coding a ServiceNow API integration, or pairing with a Data Scientist to ensure a model has the right data inputs at the right latency. You'll also architect solutions that ensure data quality, governance, and readiness for AI consumption across the ANCHOR platform. This team supports worldwide solutions covering all Amazon sites globally - you'll collaborate across time zones with engineers in France, Luxembourg, and the US.

About the team We build and deploy AI-powered agents and data solutions that automate operational workflows across Amazon's worldwide IT support, field operations, and reliability maintenance teams.

Our portfolio includes agents for automated MCM creation, printer recommendation, severity triaging, service desk automation, Data MCPs, and Analytical MCPs. We're a small, fast-moving global team with a startup-within-Amazon mentality. We ship fast, experiment boldly, and measure everything - but deploy with a high bar for production readiness.

Experience working in a high pace DevOps

• Experience with designing and building application using AWS services such as Lambda, AWS Elastic Beanstalk, Kubernetes
• Bachelor's degree in Computer Science, Engineering, a related technical field or equivalent
• 3+ years of non-internship professional software development experience (Python, Java, or equivalent) with experience designing and building distributed systems or data platforms
• Experience with data management - streaming architectures, ETL/ELT processes, data modeling, or API-based data integration, Experience with AI/ML technologies
• Experience in software development, or experience working with REST API based services and experience managing full application stacks from the OS up through custom applications
• Experience with data streaming solutions (Kinesis, Kafka, MSK), data lakes/warehouses (Redshift, S3, Glue), and ensuring data readiness for AI/ML consumption
• Experience partnering with Data Science or Data Engineering teams to build and deploy models, analytical tools, or self-service data products
• Comfort working in ambiguous environments across geographically distributed teams where you learn business processes to inform technical solutions