Senior Autonomous Security Engineer

Horizon3 AI, Inc.; Chicago, Northern (IL, KY); Hybrid; USD 169,000 - 208,000; Full time

Benefits offered by this job

Competitive pay

Equity

Health insurance

Flexible vacation

Parental leave

Remote & hybrid options

Job summary

Horizon3 is a fast-growing remote cybersecurity company dedicated to proactive vulnerability discovery and safe, scalable automation. As a Senior Software Engineer, Agentic Systems, you will build the agent harness, orchestration tooling, and the evaluation infrastructure that makes autonomous pentesting reliable at scale.

You have 5+ years of production software experience, strong Python, hands-on work with LLM-powered applications, tool use, and measurable success delivering production-ready

Qualifications

• 5+ years of production software experience.
• Strong Python development experience.
• Hands-on experience with LLM-powered applications or agents.
• Experience with tool use, function calling, and structured outputs.
• Ability to design reliable, production-grade systems.
• Familiarity with evaluation and metrics for model-driven systems.

Responsibilities

• Build and evolve the agent harness and orchestration that turns an LLM into a reliable autonomous pentester.
• Design tools and tool-shaped feedback the agent uses to probe and exploit.
• Translate offensive expertise into repeatable agent capabilities.
• Own and grow evaluation infrastructure: benchmarks and regression detection.
• Manage LLM inference in production: model selection, prompts, and cost control (AWS Bedrock).
• Hold the line on production-safety and no-false-positives.

Skills

Python

LLM apps

Production software

Agent orchestration

Evaluation/metrics

Job description

Horizon3 is a fast-growing remote cybersecurity company dedicated to proactive vulnerability discovery and safe, scalable automation. As a Senior Software Engineer, Agentic Systems, you will build the agent harness, orchestration tooling, and the evaluation infrastructure that makes autonomous pentesting reliable at scale.

You have 5+ years of production software experience, strong Python, hands-on work with LLM-powered applications, tool use, and measurable success delivering production-ready