Cyber Security Consultant

San R&D Business Solutions LLC•New York, NY

1d•Onsite

About The Position

The Cyber Security Consultant (AI Security Engineer / AI Agent Builder) will design, secure, and deploy enterprise-grade agentic AI systems. This role blends cybersecurity engineering, AI/ML development, and threat modeling to ensure autonomous AI agents operate safely, securely, and in alignment with enterprise governance standards. The ideal candidate has deep cybersecurity experience along with hands-on exposure to LLMs, AI/ML pipelines, and AI orchestration frameworks.

Requirements

10+ years of experience in cybersecurity engineering, application security, or cloud security.
Hands-on experience with LLMs, AI/ML pipelines, vector databases, and AI orchestration frameworks.
Strong programming skills (Python required; Java/C++ preferred).
Expertise in threat modeling, IAM, secure API design, and network security.
Knowledge of adversarial ML, model robustness testing, and data poisoning defense.
Experience integrating third-party AI APIs securely.
Experience implementing secure deployments in AWS/Azure/GCP.
Strong understanding of SDLC, DevSecOps, and secure architecture practices.

Nice To Haves

Experience building autonomous or multi-agent AI systems in production.
Knowledge of AI governance, responsible AI, and enterprise compliance frameworks.
Background in cryptography, secure CI/CD pipelines, and advanced MLOps.
Experience with privacy-preserving ML techniques.
Prior experience performing AI-focused red teaming.

Responsibilities

Architect and implement security controls for agent-based AI systems (identity, IAM, network segmentation, sandboxing, runtime isolation, policy enforcement).
Develop AI-specific threat models addressing adversarial prompts, agent misbehavior, data leakage, model tampering, and supply chain risks.
Design and deploy autonomous AI agents using LLMs, APIs, vector databases, and orchestration frameworks (AutoGen, CrewAI, LangGraph, etc.).
Build agent logic including tool use, routing, planning, fallback strategies, and guardrails.
Implement production-grade security monitoring pipelines for agent behavior detection.
Establish secure MLOps practices including model lineage tracking, data protection, and integrity controls.
Conduct vulnerability assessments, penetration testing, and AI red teaming.
Deploy secure AI workloads in AWS, Azure, or GCP.
Collaborate with AI research, product, cloud, and cybersecurity teams.
Contribute to AI governance frameworks and enterprise best practices for prompt security and LLM threat mitigation.