AI Software Engineer

Bishop Fox is the leading authority in offensive security, providing solutions ranging from continuous penetration testing, red teaming, and attack surface management to product, cloud, and application security assessments. We’ve worked with more than a quarter of the Fortune 100, half of the Fortune 10, eight of the top 10 global technology companies, and all of the top global media companies. Our managed service platform, service innovation, and culture of excellence continue to gather accolades from industry award programs including Fast Company, Inc., SC Media, and others. For more than 16 years, we've been contributing and giving back to the security community. We’ve published more than 16 open source tools and 50 security advisories in the last five years alone. Learn more at bishopfox.com or follow us on social media. Who You Are The Agentic AI Software Engineer – Cybersecurity Systems designs, develops, and deploys advanced AI-driven software solutions to enhance cybersecurity detection, response, analysis, and automation capabilities. This role focuses on building and maintaining agent-based artificial intelligence systems capable of autonomously generating code, conducting security analyses, triaging alerts, identifying vulnerabilities, and recommending remediation strategies, with structured human oversight and validation. The position requires the application of advanced knowledge in computer science, artificial intelligence, machine learning, secure software engineering, distributed systems, and cybersecurity principles. The role involves complex system design, secure AI integration, and the development of enterprise-grade security automation platforms. What You Will Do 1. Design and Develop Agentic AI Systems for Cybersecurity Architect and implement AI-powered systems that perform autonomous or semi-autonomous cybersecurity tasks, including vulnerability analysis, threat detection, alert triage, log analysis, and secure code review. Design multi-agent architectures capable of orchestrating specialized AI agents (e.g., vulnerability scanning agents, log analysis agents, exploit pattern detection agents). Develop retrieval-augmented generation (RAG) pipelines to enable AI systems to securely query internal knowledge bases, threat intelligence feeds, CVE databases, and security documentation. 2. AI-Assisted Secure Code Generation & Review Utilize large language models (LLMs) to generate secure software components, scripts, detection logic, and test cases. Review and refine AI-generated code to ensure compliance with secure coding standards (e.g., OWASP Top 10, secure SDLC practices). Implement automated guardrails to detect insecure outputs, prompt injection vulnerabilities, model hallucinations, and data leakage risks. Design validation frameworks to benchmark AI-generated security outputs against known vulnerability patterns. 3. Human-in-the-Loop AI Governance & Model Optimization Design and implement reinforcement learning from human feedback (RLHF) workflows for cybersecurity use cases. Develop evaluation metrics for AI accuracy in threat detection, vulnerability identification, and remediation recommendations. Continuously refine prompt engineering strategies, model tuning parameters, and system architecture to improve security reliability and precision. Implement explainability mechanisms to support auditability and defensibility of AI-driven security decisions. 4. Secure System Architecture & Integration Develop and maintain APIs and microservices to integrate AI-powered security tools into enterprise platforms. Architect scalable and fault-tolerant distributed systems to support real-time security event processing. Deploy AI-enabled services within secure cloud environments (e.g., AWS, Azure, GCP) using containerization and orchestration technologies (Docker, Kubernetes). Integrate AI systems with SIEM, SOAR, vulnerability management, and endpoint detection platforms. 5. Security Engineering & Threat Modeli