AI Security Engineer

This is a fully remote position, open to applicants in United States.

📋 Description

• Design and establish security measures for autonomous and multi-agent AI systems.

• Ensure secure orchestration of agents, execution of tools, memory management, and external integrations.

• Identify and address emerging attack vectors and vulnerabilities specific to AI.

• Safeguard Retrieval-Augmented Generation (RAG) pipelines, embeddings, vector databases, and corporate knowledge repositories.

• Create controls to prevent unauthorized access to knowledge, data leaks, and information exposures.

• Implement secure handling protocols for sensitive enterprise and healthcare data throughout AI workflows.

• Conduct threat modeling for AI applications, agent architectures, prompts, APIs, and retrieval systems.

• Evaluate risks linked to prompt injection, jailbreak attempts, indirect prompt attacks, tool misuse, hallucinations, data poisoning, model abuse, and adversarial inputs.

• Formulate mitigation strategies that diminish AI-specific security risks while ensuring usability.

• Establish guardrails that enhance trustworthy AI behavior.

• Develop policy enforcement, human-in-the-loop approval workflows, content filtering, and AI governance mechanisms.

• Assist in defining organizational standards for responsible AI development and deployment.

• Create monitoring capabilities to detect unusual agent behavior, misuse, prompt manipulation, and atypical model interactions.

• Implement logging, traceability, and auditing capabilities to support explainability and regulatory compliance.

• Develop mechanisms for ongoing AI risk assessment and operational visibility.

• Collaborate with software engineers to embed AI security within development processes.

• Perform security assessments of AI features prior to production deployment.

• Advocate for secure AI engineering practices throughout the product organization.

⛳️ Requirements

• Bachelor’s degree in Computer Science, Cybersecurity, Artificial Intelligence, Software Engineering, Information Security, or a related technical field (or equivalent professional experience).

• Over 7 years of experience in software engineering, cybersecurity engineering, AI engineering, or application security.

• Proficient in designing secure cloud-native or distributed software systems.

• Familiarity with Large Language Models (LLMs), AI applications, or Agentic AI platforms.

• Experience in securing APIs, microservices, and enterprise applications.

• Knowledge of OWASP Top 10 and secure software development methodologies.

• Understanding of AI-specific security risks, including:

• Prompt injection

• Jailbreaking

• Data poisoning

• Model abuse

• Adversarial inputs

• Hallucination mitigation

• Sensitive data leakage

• Experience with cloud security across AWS, Azure, or Google Cloud.

• Strong programming skills in Python or TypeScript.

• Excellent communication and teamwork abilities.

• A dual mindset as both a security engineer and a software engineer.

• Experience in addressing problems that currently lack established solutions.

• Ability to keep pace with emerging AI threats and defensive strategies.

• Experience with managing complex technical challenges.

• Ability to work collaboratively across various engineering disciplines.

• Capability to influence the development of secure AI systems in highly regulated environments.

• Strong ability to balance innovation with responsible engineering practices.

• Experience in securing Retrieval-Augmented Generation (RAG) systems is advantageous.

• Familiarity with AI guardrails and policy engines is a plus.

• Knowledge of frameworks such as LangGraph, LangChain, CrewAI, Semantic Kernel, AutoGen, or LlamaIndex is a plus.

• Experience with vector databases like Pinecone, Weaviate, Qdrant, Milvus, or Azure AI Search is a plus.

• Experience in implementing AI observability, evaluation, or monitoring solutions is a plus.

• Familiarity with the NIST AI Risk Management Framework (AI RMF), Responsible AI practices, or AI governance frameworks is a plus.

• Experience working in Federal Government or healthcare settings is a plus.

• Knowledge of Zero Trust Architecture and secure DevSecOps practices is a plus.

• Professional certifications such as CISSP, CCSP, Security+, GIAC, or cloud security certifications are a plus.

🏝️ Benefits

• Comprehensive benefits for you and your family.