Olivia Beyer Bruvik

I'm a graduate research assistant at the Stanford Intelligent Systems Lab working on probabilistic machine learning, uncertainty quantification, and sequential decision-making for safety-critical AI systems, advised by Prof. Mykel Kochenderfer. I'm particularly interested in how uncertainty-aware AI can be made trustworthy enough for personal, high-stakes settings - from autonomous aviation to healthcare decision-making.

I hold a B.S. in Mathematics from Stanford (2025) and am finishing my M.S. in Computer Science (AI, 2026). Previously, I interned twice at Google (Search and Cloud/Vertex AI) and at McKinsey. I also did clinical neuroimaging research at Weill Cornell Medicine.

Happy to chat at oliviabb [at] stanford [dot] edu!

Interests

Probabilistic machine learning · uncertainty quantification · integrity monitoring · AI personalization · safety-critical AI systems

Publications

Adaptive Management Strategy in Aquaculture Using Offline Belief State Planning

Bruvik, O., Eddy, D., Kochenderfer, M.

PLOS ONE, 2026. (in preparation)

BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems

Zhang, A., Bruvik, O., et al.

NeurIPS, 2025 (Datasets & Benchmarks Track).

Aircraft Localization During Surface Operations Using Segmentation Masks

Prince, E., Bruvik, O., et al.

AIAA (extended abstract), 2026. (accepted)

Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First- and Third-Party Evaluations

Reuel, A., Bruvik, O., et al.

ICML, 2026. (under review)

Disease correlates of rim lesions on quantitative susceptibility mapping in multiple sclerosis

Marcille, M., Bruvik, O., et al.

Scientific Reports, 2022.

Current Research

Stanford Intelligent Systems Lab - Research Assistant Mar 2025–Present

Runtime integrity monitoring for vision-based aircraft landing (Airbus)
Uncertainty-aware localization for autonomous aircraft taxiing (NASA ULI)
POMDP framework for aquaculture treatment under uncertainty (AquaOpt.jl)

Experience

Stanford AI Lab / CyBench - Undergraduate Researcher Dec 2024–Mar 2025
McKinsey & Company - Junior Associate Intern Summer 2024
Google Cloud, Vertex AI - STEP Intern Summer 2023
Google Search, GraphMill - STEP Intern Summer 2022
Weill Cornell Medicine - Undergraduate Researcher 2019–2022

Projects

Optimizing Sea Lice Management in Norwegian Aquaculture Using POMDPs

CS 191W Senior Research Project, Spring 2025.

Developed a Julia framework using POMDPs and offline planning to simulate, optimize, and evaluate aquaculture management strategies under uncertainty.

Role: Independent project under the supervision of Dr. Mykel Kochenderfer.

OceanAI: Prior Authorization for Health Care

Startup Project, Winter 2025. [Bot Code]

Alexa, Neel, and I worked with Stanford Health Care to automate the process from prescription to pick up. We also built a specialized Discord bot that provides medical information assistance using Mistral AI, with support for patient records, insurance information, and medical data retrieval.

Role: Created the website and implemented LLM queries, including RAG and a caching system using FAISS and Redis.

GAN-based Image Colorization Model

CS 231N Final Project, Spring 2024.

Developed a generative adversarial network (GAN) that colorizes grayscale images using semantic features extracted from a pre-trained Inception-ResNet-v2 model.

Role: Designed and implemented the model architecture, trained it using PyTorch and CUDA, and optimized performance metrics.

ExpLoRA: Exploring LoRA, SMART, and SOAP to Finetune GPT-2 for Downstream Tasks

CS 224N Final Project, Winter 2025.

Analyzed the performance of LoRA, SMART, and SOAP finetuning techniques on GPT-2 for various downstream tasks.

Role: Implemented SOAP and top-k sampling and evaluated their performance on chosen downstream tasks.

More projects

Social Computing

CS 278 Final Project, Spring 2025.

Engineered a comprehensive React Native mobile app designed to enhance and simplify dorm life for college students.

Role: Implemented parts of the backend using React Native and Supabase.

Optimizing Sea Lice Management in Norwegian Salmon Aquaculture Using Q-Learning

CS 238 Final Project, Fall 2024. [Code]

Developed a model-free reinforcement learning framework that learns optimal treatment policies for sea lice management from historical farm data.

Role: Implemented the Q-learning model with a binary action space and explored the performance of Q-learning with value function approximation.

Quarum App

Google Computer Science Summer Institute, Summer 2021. [Code]

Launched a live communication platform to enhance online lecture engagement as part of the Google Computer Science Summer Institute.

Role: Led the backend development of the website, leveraging Firebase.

Relevant Coursework