Description

Amazon Leo is Amazon’s low Earth orbit satellite network. Our mission is to deliver fast, reliable internet connectivity to customers beyond the reach of existing networks. From individual households to schools, hospitals, businesses, and government agencies, Amazon Leo will serve people and organizations operating in locations without reliable connectivity.

This role is for a Software Development Engineer who will design, implement, and operate globally distributed systems that enable Leo to achieve low single-digit-second query responses within a near real-time analytics layer or lakehouse, with a primary focus on agentic AI capabilities for autonomous operational intelligence and system optimization. You'll architect intelligent agent systems that continuously monitor, diagnose, and optimize the health and performance of Leo's satellite constellation, ground gateways, and customer terminals.

You'll build these systems using the latest AWS technologies and best-in-industry software engineering practices, creating the foundation for AI-powered operational intelligence across the Leo network.

Export Control Requirement: Due to applicable export control laws and regulations, candidates must be a U.S. citizen or national, U.S. permanent resident (i.e., current Green Card holder), or lawfully admitted into the U.S. as a refugee or granted asylum.


Key job responsibilities
- Deliver full stack contributions across front-end, back-end, data infrastructure, and AI/ML layers to build end-to-end operational intelligence systems
- Design and implement components of multi-agent AI systems that analyze satellite, ground gateway, and customer terminal telemetry to detect anomalies, predict failures, and recommend corrective actions
- Build agentic workflows that autonomously triage system anomalies, escalate critical issues based on severity and impact, and generate actionable insights for operations teams
- Develop intelligent agents capable of reasoning across distributed systems to identify root causes and coordinate collaborative problem-solving between autonomous agents, ground systems, and operations teams
- Implement reinforcement learning-based agents that optimize system performance parameters based on environmental conditions, network demand, and operational constraints
- Build natural language interfaces and RAG systems combining real-time telemetry with historical data, documentation, and knowledge bases for context-aware conversational interactions
- Design and implement hybrid search strategies combining dense vectors with sparse representations for semantic retrieval across operational patterns and system behaviors
- Implement evaluation frameworks, automated testing pipelines, and feedback loops to measure and improve agent performance, accuracy, and reliability across operational scenarios
- Design and implement components of a scalable S3-based Data Lakehouse with metadata management, automated data classification, and lineage tracking across the Leo constellation
- Implement scalable OLAP-based analytics layer components achieving low single-digit-second query responses and cross-domain federated query capabilities for near real-time analytics
- Implement globally distributed vector database infrastructure with sub-100ms retrieval times and a centralized metrics repository serving as the source of truth for all Leo operational metrics

A day in the life
This role is for a Software Development Engineer who will build new cloud services and APIs that facilitates and orchestrates simulation of software on Leo devices such as satellites, ground gateways, and customer terminals. You will be building low-latency, highly scalable architecture that are critical to getting high quality internet service to customers.

About the team
This role is for a Software Development Engineer who will build new cloud services and APIs that facilitate and orchestrate the Leo AI Foundations—enabling intelligent software operation across Leo devices such as satellites, ground gateways, and customer terminals. You will design and deliver low-latency, highly scalable architectures that are critical to providing high-quality internet service and AI capabilities to customers.