AI Security Specialist with Copilot & RedTeam experience

AI Security Specialist with Copilot & Red Team experience

Location: Remote (but should go onsite for a face-face interview @ NYC (Hudson Yards) or DC -NO RELOCATION

*CANDIDATES CAN WORK REMOTE FROM ANYWHERE BUT THEY WILL BE REQUIRED TO ATTEND ONE OR MAYBE TWO IN PERSON INTERVIEWS (TRAVEL IS NOT COVERED BY CLIENT) IN EITHER WASHINGTON DC OR NYC (HUDSON YARDS). – THE CLIENT WANTS CANDIDATES OUT OF FINANCIAL, BANKING, GOVERNMENT, INSURANCE OR OTHER HIGHLY REGULATED INDUSTRIES. ****CANDIDATES IN THE GRATER NYC OR DC AREA STRONGLY PREFERRED.*

: The AI Security Specialist safeguards the firm's use of artificial intelligence — from Microsoft Copilot and generative AI tools to internal ML models and third-party AI services. This role establishes guardrails, monitors AI usage, evaluates emerging AI products, and ensures all AI deployments meet legal, regulatory, and client confidentiality obligations.

Candidates must have Demonstrated hands-on AI red team experience — including prompt injection and jailbreak testing, adversarial ML techniques, LLM/agent abuse scenarios, and structured engagements aligned to OWASP Top 10 for LLMs and MITRE ATLAS as well as Proficiency with AI red teaming tooling such as Microsoft PyRIT, NVIDIA Garak, Promptfoo, Giskard, or comparable frameworks; ability to author custom probes and harnesses.

• Strong working knowledge of LLM architectures, RAG systems, and AI agent frameworks.
• Experience securing Microsoft 365 Copilot, Azure OpenAI, Anthropic Claude or comparable enterprise AI platforms.

Required Qualifications

• 5+ years in information security, with 2+ years focused on AI/ML security or AI governance.
• Demonstrated hands-on AI red team experience — including prompt injection and jailbreak testing, adversarial ML techniques, LLM/agent abuse scenarios, and structured engagements aligned to OWASP Top 10 for LLMs and MITRE ATLAS.
• Proficiency with AI red teaming tooling such as Microsoft PyRIT, NVIDIA...