Summary
Nastaran Okati is a research group leader and ML researcher with eight years of experience focused on making machine learning models efficient, reliable, and safe. Her work spans uncertainty quantification (conformal prediction, calibration), LLM safety alignment, provenance and watermarking, speculative decoding for efficiency, and the social and economic impacts of generative AI. She completed a PhD-level research trajectory at the Max Planck Institute for Software Systems studying predictive accuracy and fairness in human-AI teams, and has interned at Meta and multiple European research institutes where she contributed to both theoretical algorithms and applied deep learning. Based in Kaiserslautern, Germany, she blends rigorous algorithmic expertise with practical system-level thinking, often tackling questions at the intersection of robustness, transparency, and deployability. An understated strength is her track record of translating formal methods (e.g., parameterized algorithms, MDP work) into applied ML problems, signaling a rare mix of theoretical depth and application-oriented research.
8 years of coding experience
1 year of employment as a software developer
Max Planck Institute for Software Systems
Bachelor’s Degree, Computer Software Engineering, Bachelor’s Degree, Computer Software Engineering at Ferdowsi University of Mashhad
Diploma in Mathematics, National Diploma Mathematics and Physics, Diploma in Mathematics, National Diploma Mathematics and Physics at Farzanegan High School, Mashhad NODET branch
Bachelor’s Degree, Computer Software Engineering, Bachelor’s Degree, Computer Software Engineering at Sharif University of Technology
English, Persian, German