Principal Multi-Agent Security & Prompt Injection Defense Architect

Opportunity Overview

Location: 100% Remote (United States)
Employment Type: Full-Time Direct-Hire via Accel DNA
Compensation Range: $190,000 – $230,000 Base + Equity
Hiring Agency: Accel DNA – Premier Frontier Data & AI Talent Partner

Protect multi-agent autonomous enterprise deployments against indirect prompt injection, data exfiltration, tool hijack, and automated adversarial threats.

Key Responsibilities:

• Design defense-in-depth architectural layers detecting and neutralizing indirect prompt injections in untrusted emails, PDFs, and web scrapes.
• Implement least-privilege permission models and cryptographic verification for inter-agent communication channels.
• Conduct automated adversarial red-teaming against agent decision trees, tool invocation parameters, and memory stores.
• Formulate real-time monitoring sensors flagging agent behavioral divergence and unauthorized privilege escalation.

What You Bring:

• 7+ years in application security, penetration testing, or software security, with 2+ years specialized in LLM and agentic security.
• In-depth knowledge of OWASP Top 10 for LLMs, jailbreak engineering, and prompt boundary hardening techniques.
• Hands-on experience red-teaming autonomous systems and building programmatic input sanitization filters.
• BS/MS in Cybersecurity, Computer Science, or equivalent practical experience.

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/.