Note: The job is a remote job and is open to candidates in USA. The Brixton Group is seeking an AI Security Engineer to join their team responsible for securing production-grade Large Language Model (LLM) and agentic AI platforms. This role involves designing and operationalizing AI security controls, driving AI threat modeling and adversarial testing, and establishing governance frameworks to protect AI systems from various threats.

Responsibilities

• Design and implement security controls for LLM-based and agentic AI systems
• Conduct AI red teaming activities to identify vulnerabilities, prompt attacks, jailbreak techniques, data leakage risks, and unauthorized agent behaviors
• Develop automated AI safety evaluation frameworks and regression testing capabilities
• Perform threat modeling for agentic AI architectures, retrieval systems, memory components, tool integrations, and external services
• Implement runtime monitoring, detection, alerting, and incident response mechanisms for AI environments
• Translate governance, compliance, and responsible AI requirements into measurable technical controls and deployment standards

Skills

• 5+ years of AI Security experience
• AI Model Security Threat Scanning
• Agentic AI Security Development Lifecycle

Company Overview

Company H1B Sponsorship