Cybersecurity Analyst

About the Role

Reqroute, Inc is seeking a Cybersecurity Analyst – Generative AI & Agentic Automation to support enterprise-wide security initiatives. The role focuses on leveraging Generative AI and agentic engineering to automate security processes, enhance developer productivity, and embed security controls throughout the Software Development Life Cycle (SDLC). The candidate will help reduce AI-related security risks, establish secure AI engineering practices, and provide technical leadership in building scalable, reliable, and secure automation solutions.

Key Responsibilities

• Design, develop, and maintain security automation tools to improve security visibility, enforce best practices, and streamline engineering workflows.
• Build, deploy, and operationalize autonomous and semi-autonomous AI agents for enterprise security and developer productivity.
• Integrate AI agents with enterprise systems, APIs, data sources, source control platforms, CI/CD pipelines, security scanners, and developer tools.
• Develop Secure SDLC agents for requirements analysis, secure design reviews, threat modeling, code reviews, dependency analysis, vulnerability detection, remediation recommendations, and release security gates.
• Automate security checks within GitHub pull request workflows and CI/CD pipelines.
• Implement agent planning, tool usage, memory and context management, multi-agent orchestration, human-in-the-loop approvals, and failure recovery.
• Apply hands-on expertise with Anthropic Claude/Claude Code and OpenAI Codex, including prompt engineering, tool integration, API/SDK usage, evaluation, guardrails, and enterprise adoption.
• Build reusable agent tools, skills, workflows, and orchestration patterns using LangGraph, AutoGen, CrewAI, custom frameworks, and Model Context Protocol (MCP).
• Implement security controls for agent interactions, including least-privilege access, secrets protection, authorization boundaries, auditability, and approval workflows.
• Establish evaluation frameworks to measure agent performance, groundedness, code quality, secure coding, prompt-injection resistance, data leakage, unsafe tool usage, reliability, latency, and cost.
• Apply secure-by-design principles to AI-assisted development through sandboxing, policy enforcement, observability, telemetry, traceability, red-team testing, and validation of agent-generated code.
• Research emerging cybersecurity threats, zero-day vulnerabilities, security technologies, and industry trends; conduct proof-of-concept (POC) initiatives to evaluate security tools and emerging risks.
• Apply knowledge of the OWASP Top 10 and Generative AI security best practices to enterprise AI solutions.
• Support AI lifecycle management, including model integration, evaluation, monitoring, and observability.
• Provide technical leadership and mentorship in agent architecture, secure coding, AI-assisted engineering, application security, and production readiness.
• Work with Oracle, SQL, and NoSQL database architectures as required.

Requirements & Tech Stack

• Generative AI & Agentic Engineering: Claude/Claude Code, OpenAI Codex, LangGraph, AutoGen, CrewAI, MCP, prompt engineering, tool use, agent orchestration, and memory management.
• Cybersecurity & Secure SDLC: OWASP Top 10, application security, threat modeling, secure code reviews, vulnerability analysis, dependency scanning, and security gates.
• Security Automation & CI/CD: GitHub automation, pull request security checks, CI/CD integration, security tooling, and workflow automation.
• Software Engineering & Integrations: Python, JavaScript, Bash, Go/Rust/Java familiarity, API/SDK integrations, enterprise systems, and developer tooling.
• AI Security & Governance: Prompt-injection defense, data leakage prevention, least-privilege access, sandboxing, guardrails, adversarial testing, observability, and AI risk management.

Qualifications

• Bachelor’s degree in Cybersecurity, Data Science, Computer Science, Software Engineering, or a related field.
• 10+ years of software engineering experience.
• 10+ years of experience in automation and development within CI/CD environments.
• 5+ years of cybersecurity experience.
• 2+ years of hands-on Generative AI experience.
• Demonstrated experience delivering production-grade agentic AI or AI coding-agent solutions, preferably in cybersecurity, developer productivity, or Secure SDLC workflows.
• Strong proficiency in at least one scripting language: Python, JavaScript, or Bash.
• Familiarity with at least one compiled language, such as Go, Rust, or Java.
• Hands-on experience with GitHub automation, API integrations, and enterprise development workflows.
• Experience designing, building, and productionizing autonomous or semi-autonomous AI agents, including tool use, planning, context management, orchestration, and human oversight.
• Practical experience with AI coding-agent platforms such as Anthropic Claude/Claude Code and OpenAI Codex.
• Knowledge of agent frameworks such as LangGraph, AutoGen, CrewAI, or custom orchestration solutions.
• Understanding of MCP and secure integration patterns for AI agents.
• Strong knowledge of application security, OWASP Top 10, vulnerability analysis, threat modeling, and secure coding practices.
• Experience integrating automated security controls into CI/CD pipelines, pull requests, and software delivery workflows.
• Understanding of AI security risks, prompt injection, data leakage, access control, and secure agent execution.
• Knowledge of AI lifecycle management, model evaluation, observability, and production monitoring.

Preferred Qualifications:

• Master’s degree in Cybersecurity, Data Science, Computer Science, Software Engineering, or a related discipline.
• Industry certifications such as CISSP, SANS GIAC, Generative AI, or Machine Learning Operations (MLOps).
• Experience mentoring teams in application security, secure development practices, and AI-assisted engineering.
• Strong understanding of adversarial robustness techniques and machine learning security tools.
• Knowledge of AI risk management frameworks and Trustworthy AI principles.
• Experience conducting security tooling POCs and evaluating zero-day vulnerabilities and emerging cybersecurity risks.
• Familiarity with Oracle, SQL, and NoSQL database architectures.