Robert Pearce

Awards: Dean’s Honor List Medallion

Relevant coursework: Machine Learning, Computational Linear Algebra, Statistics, Operating Systems, Compilers, Databases, Cloud Computing.

Awards: Nominated for Outstanding Student in Mathematics

• Porting the kSZ zreion cosmological simulation code from CPU-based OpenMP to CUDA for GPU clusters, modernizing the Fortran codebase originally written for Bridges-2.
• Profiling the existing OpenMP routines to identify bottlenecks and prioritize the kernels with the most to gain from GPU acceleration.

• Engineered a neural network emulator for the kSZ angular power spectrum, achieving <5% prediction error while reducing inference time from hours of simulation to near real-time.
• Executed 1,000+ cosmological simulations on the Bridges-2 supercomputer via SLURM, automating 4D parameter sweeps across distributed compute nodes.
• Built a data pipeline to generate kSZ temperature maps and compute angular power spectra (C_ℓ) via Fourier transforms, extracting statistical observables of the Epoch of Reionization.
• Applied Latin Hypercube Sampling to efficiently explore multi-dimensional parameter spaces, reducing computational cost versus exhaustive grid search.
• Processed raw simulation outputs into ML-ready datasets, compressing storage requirements by 75%.

Identified and resolved 8 accessibility issues in iOS components, addressing issues related to WCAG 2.1 AA accessibility guidelines and enhancing usability for visually impaired users.

3+ years of teaching across multiple roles: SI Math Leader, Math Peer Mentor, Code Coach, and STEM Mentor. Supported 80+ students per semester in Calculus, Linear Algebra, and Statistics. Coached game development in Unity/Godot (C#, GDScript) and led robotics workshops for 200+ students using Sphero and Arduino platforms.

• Architected and published a pip-installable Python package for end-to-end scientific ML workflows: data ingestion, feature engineering, model training, and evaluation.
• Developed reusable pipelines for HDF5 data reduction and power spectrum computation, compressing intermediate data by 75% for large-scale experiments.
• Implemented a neural network emulator with Bayesian uncertainty quantification, achieving <5% error on held-out simulations with near real-time inference.
• Integrated hyperparameter optimization via Ray Tune, automated testing with PyTest, and CI/CD through GitHub Actions for reproducible experimentation.