Security Engineer/AI Agent Builder

Ampcus Inc. is a certified global provider of a broad range of Technology and Business consulting services. We are in search of a highly motivated candidate to join our talented Team.

Job Title: Security Engineer/AI Agent Builder

Location(s): New York, NY

Job Description
The Security Engineer / AI Agent Builder is responsible for designing, securing, and deploying agentic AI systems that operate safely within enterprise environments. This role blends security engineering, threat modeling, and applied AI system development-ensuring that intelligent agents operate reliably, securely, and in alignment with organizational policies.

• Architect security controls (identity, network, runtime isolation, sandboxing, policy enforcement) for agent-based AI systems.
• Develop AIspecific threat models addressing agent misbehavior, adversarial prompts, data leakage, model tampering, and supplychain risks. Evaluate thirdparty AI tools, APIs, and agent frameworks for security compliance and risk.

• Design and implement autonomous AI agents using LLMs, APIs, orchestration frameworks, and multiagent systems.
• Build agent behavior logic including tooluse, routing, planning, fallbacks, and guardrails.
• Prototype and iterate AI agents in production, refining reliability, safety, and output quality based on realworld usage.

• Develop security monitoring pipelines for agent executions and automate detection of anomalous or harmful agent behavior.
• Implement secure MLOps practices-including model lineage tracking, training data protection, and integrity controls.
• Perform vulnerability assessments, penetration testing, and redteaming of AI agents and underlying infrastructure.

• Work closely with AI research, product, engineering, cloud, and cybersecurity teams to ensure agents are performant, safe, and compliant.
• Translate business workflows into agent behaviors through scoping, discovery sessions, and requirements definition.

• Establish secure development standards for agentic AI systems and contribute to enterprise AI governance frameworks.
• Publish internal best practices for agent security, including promptsecurity guidelines, LLM threat mitigation, and safetooling patterns.

• 8+ years in cybersecurity engineering, application security, or cloud security.
• Handson experience with LLMs, AI/ML pipelines, vector databases, orchestration frameworks (AutoGen, CrewAI, LangGraph, etc.).
• Strong programming background (Python required; Java/C++ optional).
• Expertise in threat modeling, identity & access management, secure API design, and network segmentation.
• Familiarity with adversarial ML, model robustness testing, data poisoning defenses, and model evaluation.
• Experience deploying secure workloads in AWS/Azure/GCP.

• Experience building autonomous agents or multiagent systems.
• Knowledge of AI governance, safety, and responsible AI frameworks.
• Background in cryptography, secure CI/CD pipelines, MLOps, and privacypreserving ML.

Ampcus is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, protected veterans or individuals with disabilities.