Cybersecurity & AI Research Intern: AI and Software Development

About the role

We are seeking a Cybersecurity Research Intern to join our team in Princeton, New Jersey, for an internship. This role is ideal for a MSc or PhD student passionate about the potential of Large Language Models (LLMs) in supporting cybersecurity.

Responsibilities

• Engineer and refine LLM-based agents (pure vs. domain-enhanced) to act as autonomous cyber agents.
• Work on prompt engineering strategies to format network observations for optimal model reasoning.
• Design and implement Model Context Protocols (MCPs) that allow LLMs to interface securely and effectively with external security tools and environments. This includes software development tasks.
• Build data normalization pipelines to standardize events from heterogeneous sources into a unified schema.
• Define and build benchmark scenarios and evaluate agent performance against these benchmark scenarios.
• Collaborate closely with researchers and engineers across Siemens Research and Predevelopment to align research objectives with real-world applications.
• Present findings in internal reviews and contribute to top-tier publications or patents.

Requirements

• Currently enrolled full-time in a MSc or PhD program in cybersecurity, artificial intelligence, computer science, or a related field.
• Strong experience integrating LLMs into workflows (e.g., LangChain, LlamaIndex, or custom agents).
• Experience building MCP servers is a significant plus.
• Understanding of agent architectures (e.g., ReAct, Chain of Thought) and prompt engineering (formatting observations, injecting domain knowledge).
• Prior exposure to security tools such as Nessus, OpenVAS, Wazuh, Splunk, or similar.
• Understanding of common vulnerability and event log standards a significant plus.
• Proficiency in programming languages such as Python, with experience using frameworks like TensorFlow, PyTorch, or similar tools.
• Hands-on experience in Linux environments, including command-line usage and shell scripting.
• Experience with professional software development tools and workflows, such as Git, Jira, or GitLab.
• Proficiency in English both written and verbal.

Qualifications

• Strong problem-solving skills with a demonstrated ability to work on complex projects involving mathematical modeling and experimentation.
• Excellent communication skills, with the ability to articulate complex technical ideas effectively.

Preferred Qualifications

• Strong problem-solving skills with a demonstrated ability to work on complex projects involving mathematical modeling and experimentation.
• Excellent communication skills, with the ability to articulate complex technical ideas effectively.

Benefits

The challenges and responsibilities include Engineer and refine LLM-based agents (pure vs. domain-enhanced) to act as autonomous cyber agents. Work on prompt engineering strategies to format network observations for optimal model reasoning. Design and implement Model Context Protocols (MCPs) that allow LLMs to interface securely and effectively with external security tools and environments. This includes software development tasks. Build data normalization pipelines to standardize events from heterogeneous sources into a unified schema. Define and build benchmark scenarios and evaluate agent performance against these benchmark scenarios. Collaborate closely with researchers and engineers across Siemens Research and Predevelopment to align research objectives with real-world applications. Present findings in internal reviews and contribute to top-tier publications or patents.

Pay

$32- $47

Schedule

Start Time & Duration: 1 June 2026/ASAP to 18 Sep 2026 (flexible start + end dates)