onsite
Master Thesis Automated Generative AI Evaluation - BMW AG
AI Engineer
Conduct research and develop automated evaluation methods for generative AI models, leveraging Python and machine learning techniques to assess model performance and quality.
About the role
Key Responsibilities
- Design and implement automated evaluation pipelines for generative AI models using Python and relevant libraries.
- Conduct comprehensive experiments to benchmark model outputs against established metrics.
- Analyze results, identify patterns, and propose improvements to evaluation frameworks.
- Collaborate with cross‑functional teams to integrate evaluation tools into the AI development lifecycle.
- Document methodologies, findings, and best practices for future research.
Requirements
- Strong programming skills in Python and experience with machine learning libraries (e.g., PyTorch, TensorFlow).
- Solid understanding of generative AI concepts and evaluation metrics.
- Experience with data analysis, statistical evaluation, and visualization tools.
- Excellent analytical, problem‑solving, and communication skills.
- Enthusiasm for research and ability to work independently on a thesis project.
Skills
pythonmachine learninggenerative aidata analysis