Senior AI Red Team Engineer for Regulated Environments

PGTEK; Washington (District of Columbia); Hybrid; USD 150,000 - 210,000; Full time

Benefits offered by this job

Health insurance

Vision plan

Dental insurance

PTO & Holidays

Education Assistance

401(k) matching

Pet insurance discount

Employee Assistance Program

Job summary

PGTEK is seeking a Sr. Agent Security / AI Red-Team Engineer to support our L400 Advanced Development capability. You will attack our agents before adversaries do—and turn findings into durable controls for regulated and high-consequence environments.

This role requires active clearance and compliance with federal programs. The candidate will threat-model prompts, execute attacks, and design solutions using advanced AI security techniques, Model Armor, IAM, and secure tool calling, while

Qualifications

• 5+ years of software, cloud, data, cybersecurity, systems, or AI engineering experience.
• 3+ years of advanced hands-on experience in production or regulated environments.
• Experience with prompt injection, AI red teaming, Model Armor, IAM, secure tool calling, MCP/A2A security, Python, and incident response.

Responsibilities

• Threat-model prompts, retrieval, tools, memory, MCP/A2A, and identities.
• Execute attacks and verify remediation.
• Design solutions using prompt injection testing, AI red teaming, Model Armor, IAM, secure tool calling, and MCP/A2A security.
• Mentor team members and contribute reusable security standards.
• Support RMF/FedRAMP/DoD authorization activities.

Skills

Cybersecurity engineering

Python

Incident response

AI red teaming

IAM

Prompt injection testing

MCP/A2A security

Tools

Model Armor

Secure tool calling

MCP/A2A security

Job description

PGTEK is seeking a Sr. Agent Security / AI Red-Team Engineer to support our L400 Advanced Development capability. You will attack our agents before adversaries do—and turn findings into durable controls for regulated and high-consequence environments.

This role requires active clearance and compliance with federal programs. The candidate will threat-model prompts, execute attacks, and design solutions using advanced AI security techniques, Model Armor, IAM, and secure tool calling, while