Applied AI Engineer, Autonomous Defense

The role

You will build agents that turn offensive knowledge into defensive action. You will build reasoning systems that map attack paths to specific control changes and design safety architectures for autonomous changes.

What you will do

• Build reasoning systems that map attack paths to specific control changes
• Turn pentest data into training and evaluation data
• Design and run counterfactual experiments in test environments
• Design the reasoning layer over heterogeneous control planes
• Design the safety architecture for autonomous change
• Work with attack and detection engineers to define agent behavior
• Own problems end to end in a 0 to 1 environment

Required qualifications

• Strong ML engineering experience building, evaluating, and deploying production AI systems
• Hands-on work in deep learning, transformer models, and PyTorch
• Experience with post-training large language models or designing agentic systems
• Track record of building evaluation systems for open-ended tasks
• Experience reasoning over structured, heterogeneous, messy real-world data
• Strong software engineering fundamentals in Python
• Experience with data pipelines, distributed systems, and cloud infrastructure
• Ability to work across model behavior, APIs, and infrastructure
• Ability to independently research unfamiliar systems
• Strong written and verbal communication
• Master's in Computer Science, Machine Learning, or a related field, or equivalent practical experience
• 4+ years of professional engineering experience

Nice to have

• Background in detection engineering, purple teaming, security engineering, offensive security, or incident response
• Familiarity with security control planes and their APIs and policy models
• Experience with causal or counterfactual inference, or with graph reasoning, planning, and search
• Familiarity with Neo4j and attack-path analysis
• Experience building automation that takes write actions in production systems
• Experience with adversarial robustness or prompt injection
• Experience integrating ML into production, multi-tenant SaaS, or air-gapped environments

Benefits

• Equity package in the form of stock options
• Health, vision & dental insurance for you and your family
• Flexible vacation policy
• Generous parental leave

About the company

Horizon3 is a fast-growing, remote cybersecurity company dedicated to enabling organizations to proactively find and fix exploitable attack vectors. The team is a fusion of former U.S. Special Operations cyber operators, startup engineers, and formerly frustrated cybersecurity practitioners.