Intern - AI/ML Cybersecurity Advisory - Summer 2026

About Lumen

Lumen connects the world. We are igniting business growth by connecting people, data and applications – quickly, securely, and effortlessly. Together, we are building a culture and company from the people up – committed to teamwork, trust and transparency. People power progress.

 

We’re looking for top-tier talent and offer the flexibility you need to thrive and deliver lasting impact. Join us as we digitally connect the world and shape the future.

About Lumen's Internship Program

Lumen offers students a unique opportunity to gain hands-on experience in digital innovation through a 10-week summer internship. Interns learn, network, and advance their careers while helping drive technology forward - embark on your exciting journey with Lumen today

 

Come join Lumen's fully immersive, 10-week summer internship program. Our interns demonstrate curiosity, innovation, and a passion for advancing technology. We believe that empowering our people and helping them reach their full potential is essential for the long-term success of both Lumen and our customers

 

Hear from previous interns on the impact this program has had on their career. CLICK HERE!

The Role

Intern must be available to work full time (40 hours/week) during the 10-week program

 

• Program Dates: May 29 – August 7, 2026.
• Location: This position is fully remote / work from home in the continental US. 
• Work Authorization: US Work Authorization required for this role.

 

Program eligibility is contingent on the candidate’s commitment to the entire 10-week program. No exceptions will be made

The AI/ML Cybersecurity Intern will assist the Black Lotus Security Group in researching, exploring, and securing emerging AI systems and technologies. This role supports the Cyber Defense Services team in research, testing, and documentation of AI/ML security risks, as well as contributing to the development of defensive countermeasures aligned with industry frameworks such as the NIST AI RMF and Google SAIF.
Interns will gain hands-on research and experience at the intersection of cybersecurity, artificial intelligence, and machine learning.

The Main Responsibilities

• Support research and testing efforts related to AI/ML security threats such as adversarial attacks, model poisoning, prompt injection, and data leakage.
• Assist in developing and documenting methodologies for AI red-teaming and secure AI lifecycle practices.
• Contribute to the evaluation of AI/ML systems for security vulnerabilities and bias, supporting defensive and mitigation activities.
• Analyze datasets and model outputs for potential integrity and confidentiality concerns.
• Help maintain lab environments and datasets for ongoing AI adversarial testing.
• Participate in discussions and reviews related to responsible AI, fairness, and ethical implications of security testing.
• Prepare documentation, findings, and presentations for internal and external audiences.
• Collaborate with senior analysts, engineers, and researchers in the Cyber Defense Services team.

What We Look For in a Candidate

Required qualifications

• Enrolled at a 4-year accredited college or university, rising senior level education status at the start of the internship.
• Graduating August 2026 – May 2028
• Preferred fields include but not limited to: Cybersecurity or Information Security

Proficiency and understanding of:

• Coursework or research experience in machine learning, data analytics, or AI fundamentals.
• Exposure to Python, R, or Julia and comfort with scripting for data analysis or ML experimentation.
• Familiarity with basic cybersecurity principles such as threat modeling, secure coding, and vulnerability scanning

AI/ML Specific Interests:

• Demonstrated curiosity in AI/ML security, including adversarial attacks, model poisoning, prompt injection, and data leakage.
• Awareness of responsible AI frameworks (NIST AI RMF, Google SAIF).
• Knowledge of large language models (LLMs), generative AI, and agentic AI architectures.
• Interest in how attackers exploit AI systems and how defenders detect, prevent, or mitigate these risks

Tools and Hand