Sr Security Engineer, Leo Security

Description

Amazon Leo is a constellation of Low Earth Orbit satellites that will provide low-latency, high-speed broadband network connectivity to unserved and underserved communities around the world.

We are looking for a senior security engineer to join the founding cohort of the Engineering and R D team within Leo Infrastructure and IP Security. The team defends the manufacturing lines, launch sites, and global ground infrastructure behind the constellation from the most sophisticated threat actors on the planet. The team builds a neurosymbolic reasoning platform: large language model agents combined with a knowledge graph and real-time asset state store that ground every conclusion in verifiable fact, so every automated decision is auditable.

You will be the security owner for that platform. A system that can triage security events, execute containment, and act on physical security is itself a high-value target, and this role exists so the team that secures Leo does not ship its own unowned risk. This is a hands-on role for a technical contributor with deep expertise in offensive security who understands how to use AI on both sides: directing agents to test Leo's defenses the way an adversary would, and hardening the platform's own agents against the same techniques.

### Export Control Requirement

Due to applicable export control laws and regulations, candidates must be a U.S. citizen.

Key job responsibilities

You will be the single accountable security owner for every system the team builds and operates, from the agent platform and detection pipeline to the data plane and self-service workflows. You will lead threat modeling and secure-design review on each system before it takes autonomous action, thinking like an adversary to find the weaknesses in agent tool access, prompt and data injection paths, and containment authority before someone else does.

You will design the privileged-access and insider-risk controls for systems that hold the keys to Leo physical security: the who-watches-the-watchers guarantee. You will translate threat intelligence into the adversary behaviors that drive the team's models and detections, partnering with applied scientists on what to detect and with software engineers on how the platform defends itself. You will use AI to scale both offense and defense: directing the platform's agents to run offensive validation against Leo's infrastructure and against the platform itself, and turning what the offense finds into detections, guardrails, and controls.

You will drive every finding, whether from your own testing, penetration tests, or red-team engagements, to closure, with security gates built into the team's own delivery cadence rather than bolted on after.

A day in the life

One morning you might threat model a new agent capability before it graduates to automated execution, mapping what an adversary could do with its tools and where its authority must be constrained. That afternoon you could be red-teaming the platform's reasoning layer, crafting inputs that try to steer an agent into an action it should refuse. The next day you might take fresh threat intelligence, distill it into the adversary behaviors the scientists should model next, then review the access boundaries and audit evidence on a new data source before it is ingested.

You will communicate security posture, risks, and strategic priorities to senior leadership with clarity and precision. You will question every trust relationship the platform depends on, hold the security bar steady against delivery pressure, and treat the team's own systems with the same adversarial rigor the team applies to everything else.

About the team

Leo Infrastructure and IP Security protects the people, facilities, hardware, and supply chain behind a global satellite constellation. The Engineering and R D team within this organization builds the platforms and tooling the security pillar teams operate on, moving security operations from manual triage to correlation-based detection, automated response, and agentic AI. The team is composed of applied scientists, software engineers, and security engineers working across…