Job ID: JOB_ID_772
Role Overview
GAC Solutions Inc is seeking a highly specialized Security Engineer with a focus on AI Agent Building for a premier client engagement in New York, NY. This onsite contract position is at the forefront of the intersection between cybersecurity and artificial intelligence. As AI agents become increasingly integrated into enterprise workflows, the need for robust security frameworks to govern their behavior and protect organizational data has never been more critical. This role is designed for a professional who can not only build sophisticated AI systems but also ensure they are resilient against emerging threats, including adversarial attacks and data leakage.
Key Responsibilities
- Architect and implement comprehensive security controls for agent-based AI systems, including identity management, network isolation, runtime sandboxing, and policy enforcement.
- Develop and maintain AI-specific threat models to address risks such as agent misbehavior, adversarial prompts, model tampering, and supply chain vulnerabilities.
- Evaluate third-party AI tools, APIs, and agent frameworks for security compliance and risk mitigation.
- Design and implement autonomous AI agents using Large Language Models (LLMs), APIs, and orchestration frameworks like AutoGen, CrewAI, or LangGraph.
- Build agent behavior logic, including tool-use, routing, planning, fallbacks, and guardrails to ensure safe and reliable operation.
- Prototype and iterate AI agents in production environments, refining reliability and output quality based on real-world usage data.
- Develop security monitoring pipelines for agent executions and automate the detection of anomalous or harmful behaviors.
- Implement secure MLOps practices, ensuring model lineage tracking and the protection of training data throughout the lifecycle.
- Perform vulnerability assessments, penetration testing, and red-teaming of AI agents and their underlying infrastructure.
- Collaborate with cross-functional teams, including AI research, product, and cloud engineering, to align agent behaviors with business requirements.
- Establish enterprise-wide standards for secure AI development and contribute to governance frameworks.
Technical Requirements
- Minimum of 8 years of experience in cybersecurity engineering, application security, or cloud security.
- Hands-on expertise with LLMs, AI/ML pipelines, and vector databases.
- Proficiency in Python is mandatory; experience with Java or C++ is a plus.
- Deep understanding of secure API design, identity and access management (IAM), and network segmentation.
- Familiarity with adversarial machine learning, model robustness testing, and data poisoning defenses.
- Experience deploying secure workloads within major cloud environments (AWS, Azure, or GCP).
Preferred Qualifications
- Experience building autonomous agents or multi-agent systems in a production environment.
- Knowledge of AI governance, safety, and responsible AI frameworks.
- Background in cryptography, secure CI/CD pipelines, MLOps, and privacy-preserving machine learning.
This role is ideal for a security professional who is passionate about the future of AI and wants to play a pivotal role in securing the next generation of intelligent systems. If you have the technical depth and the innovative mindset required for this challenge, we encourage you to apply.
Special Requirements
Contract role. Onsite in New York. Focus on AI Agent frameworks (AutoGen, CrewAI, LangGraph).
Compensation & Location
Salary: $190,000 – $270,000 per year (Estimated)
Location: New York, NY
Recruiter / Company – Contact Information
Recruiter / Employer: GAC Solutions, Inc.
Email: sukumar@gacsol.com
Recruiter Notice:
To remove this job posting, please send an email from
sukumar@gacsol.com with the subject:
DELETE_JOB_ID_772