Anya von Diessl

Mathematics Department Tutor & Grader at Stanford

Provided advanced instruction in theoretical and applied mathematics through Stanford’s Mathematics Department. Guided students through rigorous explorations of vector space theory, multivariable analysis, and differential systems, with specialized focus on spectral and matrix theory, eigenvalue and singular value decomposition (SVD), dimensionality reduction, proof construction, and the analysis of linear operators and dynamical systems. Graded coursework and examinations for four undergraduate mathematics courses, working closely with Stanford Mathematics Department professors.

Statistical Modeling & Inference Researcher at Stanford

Conducted research on latent-variable and probabilistic models for uncertainty quantification in high-dimensional, noisy datasets. Developed and implemented Bayesian inference frameworks and variational optimization algorithms to uncover hidden structure and mitigate estimation bias in predictive modeling. Leveraged stochastic process theory, information-theoretic measures, and causal inference techniques to enhance model identifiability, interpretability, and robustness in complex real-world systems.

Machine Learning Researcher at Stanford CS Department

Developed a contrastive deep learning model to identify regulatory differences in chromatin accessibility across normal, tumor, and metastatic states. By leveraging CNN architectures like ChromBPNet, applied advanced machine learning techniques to enhance the precision of sequence-to-function predictions, with a focus on refining computational models for disease progression, particularly in thyroid cancer.

Teaching Assistant, CS227b: General Game Playing at Stanford CS Department

Assisted in teaching a graduate-level AI course on the design of autonomous agents capable of strategic reasoning in novel environments. Guided students in applying methods from automated reasoning, symbolic knowledge representation, adversarial and heuristic search, resource-bounded planning, and algorithmic game theory to develop general-purpose intelligence systems that learn and execute strategies from formal game descriptions.

Computational Modeling Researcher at Stanford Translational AI Lab

Conducted interdisciplinary research uniting artificial intelligence, probabilistic modeling, and computational medicine. Developed and deployed deep learning architectures for computer vision and medical imaging, integrating probabilistic inference to quantify uncertainty and extract high-fidelity biomarkers. Leveraged Bayesian and data-driven modeling frameworks to improve diagnostic prediction, enhance model interpretability, and advance precision healthcare through statistically robust AI systems.

Google Ads SWE Intern at Google

Developed a high-performance, production-scale interface for a real-time fraud detection platform within Google Ads, leveraging TypeScript, HTML, and CSS to engineer modular, scalable, and latency-optimized components. Collaborated with cross-functional teams to translate complex fraud analytics pipelines and anomaly detection workflows into intuitive, data-rich visual systems, enhancing usability, reliability, and decision speed across a platform processing billions of ad transactions daily.