Software Development Engineer , Leo Regulus
Posted Updated
Amazon Leo is bringing satellite internet to 100+ countries — and before we can sell in any of them, an enormous amount of behind-the-scenes checking has to pass: is every customer charged correctly, is tax right for that country's laws, does money move to the right accounts, are the invoices legally valid, does the whole buy-and-activate experience actually work end to end? Today, dozens of teams work through this by hand, one step after another, for months. It's the single biggest thing standing between "we're ready" and "we've launched" — and we're replacing that entire process with AI.
Leo Regulus is an AI-native team building squads of autonomous agents that compress Leo's launch process from months to days. The agents run in parallel, share context across every domain a launch touches — tax, accounting, payments, legal, trade, and commerce — and get smarter with each country we ship. Crucially, we don't do the manual work; we build the agents that do it, and do it better each time. Instead of writing the checks by hand, we build agents that write, run, diagnose, and fix them.
This is a rare kind of problem: real autonomy with real stakes — these agents gate a global product launch — and genuine cross-domain reasoning, because a single launch spans law, finance, payments, and the shopping experience all at once, and the agents have to keep each other in sync. You don't need any background in testing or launch operations; you need to be great at building intelligent systems and excited by agentic AI as the product itself — designing how agents plan, act, check their own work, recover from failure, and learn. If building the AI team that launches satellite internet across the planet — in minutes instead of months — sounds like the most interesting thing you could work on, let's talk.
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
Key Job Responsibilities:
*Design and build autonomous AI agents that execute end-to-end ecommerce validation without human intervention
- Build orchestration systems that coordinate dozens of domain-specific agents working in parallel
- Create knowledge base architectures that ground agent behavior in accounting, tax, and compliance rules
- Solve novel problems at the intersection of AI, distributed systems, and financial domain complexity
A day in the life
An SDE on Leo Regulus will be responsible for designing, building, and operating autonomous AI agent systems that automate the end-to-end ecommerce launch lifecycle — from requirements generation through financial configuration, test execution, and validation — enabling Amazon Leo to scale country and feature launches across 100+ markets without proportional headcount growth.
About the team
We are a team building the AI infrastructure that makes Amazon Leo's 100-country launch possible. Our entire stack is AI-native — every system we build either is an agent, powers an agent, or feeds an agent. We don't maintain legacy test frameworks or manual runbooks. We build autonomous systems and point them at problems that would otherwise require hundreds of engineers.
Leo Regulus is an AI-native team building squads of autonomous agents that compress Leo's launch process from months to days. The agents run in parallel, share context across every domain a launch touches — tax, accounting, payments, legal, trade, and commerce — and get smarter with each country we ship. Crucially, we don't do the manual work; we build the agents that do it, and do it better each time. Instead of writing the checks by hand, we build agents that write, run, diagnose, and fix them.
This is a rare kind of problem: real autonomy with real stakes — these agents gate a global product launch — and genuine cross-domain reasoning, because a single launch spans law, finance, payments, and the shopping experience all at once, and the agents have to keep each other in sync. You don't need any background in testing or launch operations; you need to be great at building intelligent systems and excited by agentic AI as the product itself — designing how agents plan, act, check their own work, recover from failure, and learn. If building the AI team that launches satellite internet across the planet — in minutes instead of months — sounds like the most interesting thing you could work on, let's talk.
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
Key Job Responsibilities:
*Design and build autonomous AI agents that execute end-to-end ecommerce validation without human intervention
- Build orchestration systems that coordinate dozens of domain-specific agents working in parallel
- Create knowledge base architectures that ground agent behavior in accounting, tax, and compliance rules
- Solve novel problems at the intersection of AI, distributed systems, and financial domain complexity
A day in the life
An SDE on Leo Regulus will be responsible for designing, building, and operating autonomous AI agent systems that automate the end-to-end ecommerce launch lifecycle — from requirements generation through financial configuration, test execution, and validation — enabling Amazon Leo to scale country and feature launches across 100+ markets without proportional headcount growth.
About the team
We are a team building the AI infrastructure that makes Amazon Leo's 100-country launch possible. Our entire stack is AI-native — every system we build either is an agent, powers an agent, or feeds an agent. We don't maintain legacy test frameworks or manual runbooks. We build autonomous systems and point them at problems that would otherwise require hundreds of engineers.