Remote Autonomous Defense AI Engineer

Horizon3; United States; Remote; USD 140,000 - 210,000; Full time

Benefits offered by this job

Growth opportunities

Innovation-driven culture

Flexible work environment

Inclusive and Diverse Team

Job summary

Horizon3 is seeking an AI Researcher to build autonomous agents that translate proven attack paths into concrete defender actions across production environments. You will work on systems that reason from telemetry to specific control changes, with real outcome signals from pentests and deployments.

You will design the safety and governance layers for autonomous changes, ensure changes are auditable, and collaborate with attack engineers and detection teams to learn from failures and improve

Qualifications

• Master’s degree in CS/ML or related field with 4+ years of engineering experience.
• Strong ML/AI background with production-grade systems.
• Experience with security-focused AI or incident response is a plus.

Responsibilities

• Build agents that map attack paths to actionable control changes in production environments.
• Design and run closed-loop defense systems at enterprise scale.
• Collaborate with attack engineers and detection teams to diagnose failures and improve safety.
• Develop the safety architecture for autonomous changes, including dry-run, rollback, and audit trails.

Skills

ML engineering

PyTorch

Deep learning

Python

Security engineering

Distributed systems

Cloud (AWS)

Graph reasoning

Offensive security

Counterfactual inference

Education

Master's in CS/ML or related field

Tools

Neo4j

AWS

Splunk

Job description

Horizon3 is seeking an AI Researcher to build autonomous agents that translate proven attack paths into concrete defender actions across production environments. You will work on systems that reason from telemetry to specific control changes, with real outcome signals from pentests and deployments.

You will design the safety and governance layers for autonomous changes, ensure changes are auditable, and collaborate with attack engineers and detection teams to learn from failures and improve