Aktiviere Job-Benachrichtigungen per E-Mail!

Master Thesis Embedded Pentesting with AI Agents

Robert Bosch Group

Renningen

Vor Ort

EUR 40.000 - 60.000

Vollzeit

Vor 14 Tagen

Zusammenfassung

A leading company seeks a Master's student for a thesis in Embedded Pentesting with AI Agents. The role involves developing AI-driven cybersecurity solutions, designing modular architectures for embedded systems, and implementing a specialized pentesting agent. Candidates should have a strong background in security, embedded systems, and programming, alongside excellent English or German language skills.

Qualifikationen

  • Education: Master studies in Computer Science or a comparable field with excellent academic performance.
  • Experience and Knowledge: Background in security and/or embedded systems.
  • Languages: Very good command of English or German.

Aufgaben

  • Develop innovative solutions for embedded system pentesting using AI agents.
  • Design and implement a modular testbench architecture for AI interaction.
  • Evaluate solutions with real embedded devices against traditional methodologies.

Kenntnisse

Background in security
Embedded systems knowledge
Programming skills in Python
Knowledge of pentesting methods

Ausbildung

Master studies in Computer Science or comparable field

Jobbeschreibung

Master Thesis Embedded Pentesting with AI Agents

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people's lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other.

Join in and feel the difference.

The Robert Bosch GmbH is looking forward to your application!

Responsibilities
  • During your Master thesis, you will advance research in AI-driven cybersecurity by developing innovative solutions for embedded system pentesting using large language model agents.
  • You will design and implement a modular testbench architecture that enables AI agents to interact with embedded hardware through standardized interfaces, including power supplies, communication protocols (CAN, Ethernet, UART, SPI, I2C), as well as monitoring equipment.
  • Furthermore, you will implement a Model Context Protocol (MCP) server to create seamless communication between AI agents and embedded hardware components, enabling autonomous security assessments.
  • Additionally, you will develop a specialized AI pentesting agent capable of device reconnaissance, vulnerability identification, and exploit development, while documenting findings for interdisciplinary security teams.
  • Finally, you will evaluate your solution through comprehensive testing against real embedded devices from automotive and IoT domains, comparing AI-driven approaches with traditional pentesting methodologies to validate effectiveness and identify areas for improvement.
Requirements
  • Education: Master studies in Computer Science or a comparable field with excellent academic performance.
  • Experience and Knowledge: Background in security and/or embedded systems; knowledge of basic pentesting methods; programming skills in Python.
  • Personality and Working Practice: Highly motivated to learn and have an independent working style.
  • Languages: Very good command of English or German.
Additional Information

Start: according to prior agreement

Duration: 6 months

Requirement for this thesis is enrollment at a university. Please attach your CV, transcript of records, examination regulations, and if applicable, a valid work and residence permit.

Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore, we welcome all applications, regardless of gender, age, disability, religion, ethnic origin, or sexual identity.

Need further information about the job?

Dr. Max Eisele (Functional Department)
+49 173 2527116

Dr. Christopher Huth (Functional Department)
+49 172 6760590

#LI-DNI

Hol dir deinen kostenlosen, vertraulichen Lebenslauf-Check.
eine PDF-, DOC-, DOCX-, ODT- oder PAGES-Datei bis zu 5 MB per Drag & Drop ablegen.