AI Security Red Team Engineer - Offensive Cyber for AI

Software Engineering Institute | Carnegie Mellon University; Pittsburgh (Allegheny County); On-site; USD 130,000 - 180,000; Full time

Job summary

Software Engineering Institute (SEI) at Carnegie Mellon University is seeking an AI Red Team Engineer on the AI Security team. You will drive adversary emulation and capability development for national security contexts, operating across AI-enabled platforms with offensive cyber expertise.

Candidates should be versed in Windows/Linux, TCP/IP, and pen-testing with strong communication skills. Role demands graduate-level courses or certifications while travelling to partner sites and conferences.

Qualifications

• Extensive experience in penetration testing and red-teaming for secure systems.
• Hands-on with at least one command-and-control framework and offensive cyber tradecraft.
• Proficiency programming/scripting in Python, C, and BASH; ability to learn PowerShell.
• Familiarity with reverse engineering tools and vulnerability assessment across Linux/Windows.

Responsibilities

• Red-team real-world AI-enabled systems to assess security objectives.
• Develop new tactics, techniques, and procedures for attacking AI-enabled platforms.
• Write tools in Python, PowerShell, C, and BASH for red-team ops.
• Represent CERT portfolio and communicate with mission partners and teams.
• Travel up to 25% for field sites, conferences, and offsite meetings.

Skills

Penetration testing

Red teaming

Exploit development

Python

C

BASH

PowerShell

Wireshark

TCP/IP

OS security (Linux/Windows)

Cobalt Strike

Sliver

IDA Pro

Ghidra

OSCP

CPTS

CCNA

Education

BS in computer science, software engineering, networking, information systems, or related

MS in computer science or technical/engineering field

PhD in computer science or technical/engineering field

Tools

Cobalt Strike

Sliver

NSAGhidra

IDA Pro

Wireshark

Job description

Software Engineering Institute (SEI) at Carnegie Mellon University is seeking an AI Red Team Engineer on the AI Security team. You will drive adversary emulation and capability development for national security contexts, operating across AI-enabled platforms with offensive cyber expertise.

Candidates should be versed in Windows/Linux, TCP/IP, and pen-testing with strong communication skills. Role demands graduate-level courses or certifications while travelling to partner sites and conferences.