Senior AI Red Teaming & Adversarial Robustness Engineer

Opportunity Overview

Location: 100% Remote (United States)
Employment Type: Full-Time Direct-Hire via Accel DNA
Compensation Range: $180,000 – $215,000 Base + Bonus
Hiring Agency: Accel DNA – Premier Frontier Data & AI Talent Partner

Spearhead automated adversarial testing, jailbreak vulnerability research, and agent privilege escalation defenses for autonomous enterprise systems.

Key Responsibilities:

• Design automated multi-turn adversarial prompt testing frameworks that simulate advanced persistent threat (APT) agent exploits.
• Identify indirect prompt injection vulnerabilities in web-connected agents, RAG pipelines, and tool-calling interfaces.
• Build automated regression suites validating that model updates do not introduce security bypasses.
• Work alongside AI engineering squads to implement robust input sanitization, least-privilege tool execution, and sandbox isolation.

What You Bring:

• 5+ years in application security, penetration testing, or AI safety research.
• Proven expertise in prompt injection mechanics, ASCII smuggling, jailbreaking, and multi-modal adversarial attacks.
• Proficiency in Python and security automation scripting.
• OSCP, CISSP, or demonstrated contributions to AI vulnerability disclosure programs.

How to Apply:

Interested in exploring this opportunity? Submit your profile or portfolio directly to contact@accel-dna.com or apply through https://accel-dna.com/contact-us/.