Research Assistant (E13, Machine Learning and Security Group, IV-47/26)
Research Assistant (E13, Machine Learning Group, IV-40/25)
About us
The Chair of "Machine Learning and Security" at the BIFOLD institute is seeking a research associate (PhD student) for a project within the Excellence Cluster CASA. The project focuses on the security of Large Language Models (LLMs). Its goal is to use differential testing to identify behavioral differences in LLM across model variants, software stacks, and hardware platforms.
The project aims to assess whether these differences affect the security of the models and how the resulting risks can be mitigated.
Your responsibility
- Research and security analysis of LLMs
- Differential testing of LLM implementations
- Development of protection mechanisms for LLMs
- Academic publishing
There is the possibility of pursuing a doctorate.
Your profile
- Successfully completed university degree (Master, Diplom or equivalent) in Computer Science or a related technical field
- Strong knowledge and skills in machine learning
- Strong knowledge and skills in computer security
- Experience with (differential) software testing
- Good knowledge of German and/or English required; willingness to acquire the respective missing language skills
- Ability to work both independently and collaboratively, with a high level of initiative
Employer: TU Berlin / BIFOLD
Salary grade: TV-L E13
Starting date: earliest possible
Closing date: February 27, 2026
Full job posting: IV-47/26