Senior Software Engineer

This is a fully remote position, open to applicants in United States.

📋 Description

• Develop and enhance the agent harness and orchestration that transforms an LLM into a dependable autonomous pentester, creating a loop that analyzes an application, formulates attack hypotheses, executes actions, and verifies outcomes.

• Create the tools and tool-shaped feedback mechanisms that the agent utilizes to probe and exploit, along with the structured-output and validation layers that ensure reliability (e.g., hook-enforced mandatory validation, schema-constrained outputs).

• Convert the team's offensive expertise into repeatable agent functionalities — collaborating directly with our attackers to encapsulate their thought processes into actions the agent can perform consistently.

• Oversee and expand our evaluation infrastructure: benchmark suites, a failure-mode taxonomy across the pipeline (discovery → hypothesis → exploitation → verification), and regression detection, to ensure we can ascertain whether the agent is improving.

• Manage LLM inference in a production environment: model selection, prompt and context engineering, while keeping costs and latency manageable (we operate on AWS Bedrock with centralized cost tracking).

• Maintain high standards on production safety and ensure no false positives; every finding reported by the agent must be genuine and reproducible.

⛳️ Requirements

• Over 5 years of experience in building production software, with a strong proficiency in Python.

• Practical experience in developing LLM-powered applications or agents, including tool usage/function calling, structured outputs, multi-step orchestration, and the integration that binds it all together.

• Proven history of making LLMs reliable in production; you have dealt with nondeterminism, designed solutions around model limitations, and delivered functional products when it mattered most.

• Genuine experience with evaluation: you have built or managed the framework that assesses whether a model or agent modification is an enhancement, rather than just a feeling.

• Strong intuition for prompt and context engineering, along with the discernment to keep the model's responsibilities focused and manageable.

• Solid grounding in software fundamentals — testing, observability, and the discipline to ensure a complex agent remains debuggable.

• An ownership mindset, comfortable taking responsibility for a critical, fast-evolving subsystem from start to finish.

🏝️ Benefits

• Health, vision & dental insurance for you and your family

• Flexible vacation policy

• Generous parental leave

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

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

• 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.