PhD Student - Privacy Enhancing Technologies for LLMs and AI Agents

Huawei; München; On-site; EUR 40,000 - 55,000; Full time

Benefits offered by this job

Healthy meals in company canteen

Training opportunities including language courses

Support for publishing in leading conferences

Job summary

Huawei's Munich Research Center is seeking a PhD Student to research Privacy Enhancing Technologies for AI and LLMs. The role involves conducting research on privacy risks in AI systems, developing novel methods, and collaborating for real-world applications. Candidates should have a Master’s degree in a related field and strong machine learning skills. The position offers competitive compensation and opportunities for publication. Join our multicultural team to shape the future of trustworthy intelligent systems.

Qualifications

• Master’s degree (or equivalent) in computer science, mathematics, electrical engineering, or related field.
• Strong theoretical and practical background in machine learning, deep learning, or natural language processing.
• Proficient programming skills in Python and experience with at least one major deep learning framework.

Responsibilities

• Conduct systematic research on privacy risks in AI agent systems.
• Develop novel privacy-preserving methods to mitigate risks.
• Explore and apply privacy frameworks to agent-based architectures.

Skills

Machine learning

Deep learning

Natural language processing

Python programming

Deep learning frameworks (PyTorch, TensorFlow, JAX)

Research experience in ML/security/privacy

English proficiency

Education

Master’s degree in computer science or related field

Job description

PhD Student – Privacy Enhancing Technologies for LLMs and AI Agents (m/f/d)

Huawei's Munich Research Center is responsible for advanced technology research, architectural development, design and strategic engineering of our products.

Artificial Intelligence agents are rapidly becoming part of everyday life, however, they also introduce significant privacy risks: sensitive information may be unintentionally memorized, exposed across agent interactions, or leaked through internal reasoning and decision processes.

Our research group focuses on the intersection of Privacy, Security, and Artificial Intelligence, with a particular emphasis on privacy risks in LLM-based and multi‑agent systems. Our goal is to design novel privacy‑enhancing technologies that make next‑generation AI agents trustworthy, secure, and deployable in real‑world applications.

We are looking for a highly motivated PhD candidate who is excited about cutting‑edge research in AI and privacy, and who wants to contribute to shaping the future of trustworthy intelligent systems.

Your Responsibilities

• Conduct systematic research on privacy risks in AI agent systems, with a focus on components such as memory, reasoning, decision‑making, and multi‑agent communication.
• Develop novel privacy‑preserving methods to mitigate risks such as sensitive data leakage, prompt‑based extraction, unintended memorization, and privacy violations during agent collaboration.
• Explore and apply privacy frameworks to agent‑based architectures.
• Design, implement, and evaluate prototypes in realistic LLM‑ and multi‑agent environments.
• Publish your research in leading conferences and journals in machine learning, AI security, and privacy (e.g., NeurIPS, ICML, ICLR, CCS, S&P, PETS).
• Collaborate with academic and industrial partners to transfer research results into real‑world systems and products.

Your Areas of Expertise

• Master’s degree (or equivalent) in computer science, mathematics, electrical engineering, or a related field.
• Strong theoretical and practical background in machine learning, deep learning, or natural language processing.
• Proficient programming skills in Python and experience with at least one major deep learning framework (e.g., PyTorch, TensorFlow, or JAX).
• Familiarity with large language models and agent‑based systems is a plus.
• Knowledge of privacy and security techniques relevant to ML systems is a plus.
• Prior research experience or publications in machine learning, security, or privacy venues is advantageous.
• Excellent written and spoken English.

If you are enthusiastic to shape the German Research Center in Munich together with us, being part of a multicultural team and growing environment, feel free to contact us. Driving future technologies with focus on customer satisfaction is one of our missions. Join us!

Your Rewards of Working Here

• Our culture is characterized by innovative power and team spirit as well as the intensive exchange of knowledge and experience within our global network.
• We offer healthy meals ranging from traditional Chinese to western delicacies in our famous company canteen.
• To keep your development ongoing, you will find a broad range of training opportunities. Many online and face‑to‑face training programs incl. language courses in German and Mandarin.
• Our diverse and welcoming environment is shaped by different backgrounds and around 40 individual nationalities.
• Competitive compensation and benefits.
• Strong support for publishing in leading conferences and journals, including mentorship, collaboration opportunities, and resources to conduct high‑impact research.
• The opportunity to contribute research that informs and transitions into real‑world products, influencing privacy features in deployed LLM‑ and agent‑based systems.
• Ability to transform research prototypes into customer‑facing products.

Please send your application and CV (incl. cover letter and reference letters) in English.

By applying to this position, you agree with our Recruitment Privacy Statement. You can read in full our privacy policy here.