Senior Software Engineer, Agentic Systems

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

At Horizon3, we’re building a team of bold thinkers, problem solvers, and Learn-it-Alls.
We’re looking for individuals who:

Love solving tough problems, especially the ones no one else has cracked.

Thrive in high-performing teams that celebrate success and lift each other up.

Have the grit and tenacity to take on complex, mission-critical challenges.

Want to make a real impact by helping organizations stay ahead of attackers.

Continuously learn and adapt, embracing new technologies, perspectives, and ideas.

Are passionate about disruption, driving innovation in the cybersecurity space.

If you’re eager to grow, driven to contribute, and ready to shape the future of cybersecurity, we want to hear from you.

The Perks of working with Horizon3

Our Culture

We’re a team of “learn-it-alls” who love building awesome products. From intern to CEO, we celebrate diversity and bring a wide array of experience from technology startups, Fortune 500s, and the US Military.

Remote Work Options

With offices in San Francisco, Chicago, and Amsterdam, we have hybrid and remote positions available globally.

Build Something Meaningful

We’re motivated to create a safer, more secure environment, convert new ideas to exceptional solutions and deliver great customer experiences.

Be part of a passionate and talented team which have entrepreneurial spirit, because it makes a huge difference.

Think Long Term

You’ll have complete ownership and responsibility along with huge potential for growth. We envision the future and build it one step at a time.

Competitive pay, great health & dental care for you and your loved ones, and a 4 weeks + generous holidays and vacation packages globally.

Positions

We’re a remote-first company with teammates clustered around the globe.

Senior Software Engineer, Agentic Systems

Location

US, Remote

Employment Type

Full time

Location Type

Remote

Department

Get to Know Us

Horizon3 is a fast-growing, remote cybersecurity company dedicated to the mission of enabling organizations to proactively find, fix, and verify exploitable attack vectors before criminals exploit them. Our flagship product, the NodeZero™ platform, delivers production-safe autonomous pentests and other key assessment operations that scale across the largest internal, external, cloud, and hybrid cloud environments. NodeZero has been adopted by organizations of all sizes, from small educational institutions to government agencies and Global 100 enterprises. It is used by ITOps/SecOps teams, consulting pentesters, and MSSPs and MSPs.

We are a fusion of former U.S. Special Operations cyber operators, startup engineers, and formerly frustrated cybersecurity practitioners. We're committed to helping solve our common security problems: ineffective security tools, false positives resulting in alert fatigue, blind spots, "checkbox" security culture, the cybersecurity skills shortage, and the long lead time and expense of hiring outside consultants. Collectively, we are a team of learn-it-alls, committed to a culture of respect, collaboration, ownership, and results.

Summary

We're building an autonomous, black-box web application penetration tester. It crawls and attacks real production websites the way a skilled human pentester would, finding broken access control, injection, XSS, SSRF, SSTI, and more, under a strict production-safe, no-false-positives mandate.

We have deep offensive expertise on this team: people who know exactly how to find and exploit these vulnerabilities by hand. What we need is an engineer who can turn that expertise into autonomous agent capability, the reasoning, orchestration, tooling, and evaluation that lets an LLM-driven agent do this work reliably, at scale, and unattended. You'd own and evolve the attack-agent layer: the part of the system that decides what to probe, forms and tests hypotheses, exploits, and verifies, without false positives and without touching anything it shouldn't.

This is a build role, not a research role. We use models surgically, deterministic-first, LLM-as-scalpel, and the hard problems are in engineering reliability, not chasing benchmarks.

Essential Functions

Build and evolve the agent harness and orchestration that turns an LLM into a reliable autonomous pentester, the loop that reasons over an application, forms attack hypotheses, acts, and verifies results.

Design the tools and tool-shaped feedback the agent uses to probe and exploit, and the structured-output and validation layers that keep it reliable (e.g., hook-enforced mandatory validation, schema-constrained outputs).

Translate the team's offensive expertise into repeatable agent capabilities — partnering directly with our attackers to encode how they think into something the agent can do consistently.

Own and grow our evaluation infrastructure: benchmark suites, a failure-mode taxonomy across the pipeline (discovery → hypothesis → exploitation → verification), and regression detection, so we actually know whether the agent is getting better.

Manage LLM inference in production: model selection, prompt and context engineering, and keeping cost and latency under control (we run on AWS Bedrock with centralized cost tracking).

Hold the line on production-safety and no-false-positives, every finding the agent reports has to be real and reproducible.

5+ years building production software, with strong Python.

Hands-on experience building LLM-powered applications or agents, tool use / function calling, structured outputs, multi-step orchestration, and the glue that makes it all hold together.

A track record of making LLMs reliable in production, you've wrestled nondeterminism, designed around model limitations, and shipped something that worked when it mattered.

Real experience with evaluation: you've built or owned the harness that tells you whether a model or agent change is an improvement, not just a vibe.

Strong instincts for prompt and context engineering, and the judgment to keep the model's job small and well-scoped.

Solid software fundamentals — testing, observability, and the discipline to keep a complex agent debuggable.

Ownership mentality, comfortable owning a critical, fast-moving subsystem end to end.

Desired/Nice to Have

Working knowledge of web application security, broken access control, IDOR/BOLA, SQLi, XSS, SSRF, SSTI, enough to collaborate fluently with offensive engineers.

Experience building eval harnesses or benchmarks specifically for agents (synthetic environments, CVE-based test targets, capture-the-flag-style scoring).

Experience with agent frameworks, and strong opinions about when not to reach for one.

Familiarity with graph data models (e.g., Neo4j) for representing application state and attack context.

What makes you stand out:

You've shipped an autonomous agent that did real, valuable work unattended in production, and you have scar tissue from making it trustworthy.

You've designed evaluation systems that actually drove improvement, closed the loop between "we changed something" and "it measurably got better."

You pair an offensive-security mindset (CTF, bug bounty, pentesting, or research background) with the engineering chops to turn that intuition into a reliable system.

You have hands-on experience with agent fine-tuning or RL (SFT, GRPO, reward design for tool-using agents) and a grounded view of when it's worth it versus improving the harness.

You've published or spoken on agent reliability, evaluation, or autonomous security tooling.

Perks of Horizon3

Inclusive Team: We value diversity and promote an inclusive culture where everyone can thrive.

Growth Opportunities: Be part of a dynamic and growing team with numerous career development opportunities.

Innovative Culture: Work in a collaborative environment that encourages creativity and out-of-the-box thinking.

Hybrid & Remote Work: We embrace a mix of remote and hybrid work models depending on role and location, including our Chicago office, where some roles require regular in-office presence.

Competitive Compensation: We offer competitive salary, equity and benefits. Our benefits include health, vision & dental insurance for you and your family, a flexible vacation policy, and generous parental leave.

Compensation and Values

At Horizon3, we believe that our people are our greatest asset, and our compensation philosophy reflects this core value. We are committed to fostering an environment where all employees feel valued, respected, and rewarded for their contributions. Our compensation structure is designed to be fair, competitive, and transparent, ensuring that every team member is recognized and compensated equitably across roles, levels, and locations.

In accordance with various State’s transparency regulations, we provide the following salary range information for this position:

Base salary range: $169,000 - $208,000 annually. The exact salary will be determined based on the selected candidate’s location, qualifications, experience, and relevant skills.

Additional compensation: All full-time roles are eligible for an equity package in the form of stock options.

You Belong Here

Horizon3 is not just an equal opportunity employer - we are a community that values diversity, equity, and inclusion as fundamental principles of our culture and success. We are dedicated to fostering a workplace where everyone feels welcome and respected, regardless of race, color, religion, sex, national origin, age, disability, veteran status, sexual orientation, gender identity or expression, genetic information, marital status, hair length or any other legally protected status by law.

Our commitment to diversity and inclusion means we strive to attract, develop, and retain a workforce that reflects the varied communities we serve. We believe that diverse perspectives drive innovation and strengthen our ability to create cutting-edge cybersecurity solutions. At Horizon3, every team member is valued and supported in an environment that encourages personal and professional growth.

We welcome candidates from all backgrounds and experiences, and we encourage all qualified individuals to apply. Come be a part of Horizon3, where your unique contributions are recognized, and your potential is limitless.

Other Duties

Please note this job description is not designed to cover or contain a comprehensive listing of activities, duties or responsibilities that are required of the employee. Duties, responsibilities, and activities may change at any time with or without notice.