The public PDF leaves out my phone number and email address.
Email me
for a copy with full contact details.
Experience
AI/ML Scientist
May 2026 – Present
Los Alamos National Laboratory, Los Alamos, NM
Build and validate end-to-end ML pipelines (data ingestion, preprocessing, feature engineering, training, and evaluation) for large-scale multiphysics simulations.
Deploy models into production HPC codes with performance monitoring, and support the scientists who use them.
Develop LLM and RAG assistants over domain-specific technical documents, including retrieval, grounding, and scoring generated answers against expert-labeled ground truth before release.
Create frameworks for large physics codes using AI coding agents (Claude Code, Codex, and OpenCode), and run Claude on a government-hosted cloud platform.
Work with research, engineering, and end-user groups across the lab to turn their requirements into deployed models, and make the case for adopting them.
Metropolis Postdoctoral Fellow
Feb 2025 – May 2026
Los Alamos National Laboratory, Los Alamos, NM
Trained reinforcement learning agents for sequential decisions that reduce error in numerical simulations, including custom environment design and reward engineering.
Applied ML-driven optimization to energy group structures for nuclear data, reducing data size while keeping simulation accuracy within tolerance.
Prototyped LLM and RAG applications for technical document search and simulation workflows, and compared local and hosted inference.
Replaced expensive linear-algebra kernels in transport simulations with learned surrogates (autoencoders, deep neural networks, and deep operator networks), reducing data within a prescribed error tolerance.
Built open-source Python, Cython, and C++ transport libraries with API documentation and regression tests.
Developed a single-grid error estimation method for verifying high-dimensional solvers, published in the Journal of Verification, Validation and Uncertainty Quantification.
Graduate Student Assistant
Jun 2021 – Aug 2021
Lawrence Livermore National Laboratory, Livermore, CA
Integrated parallel C++ production physics codes on Livermore's HPC systems.
Worked with several developer teams and their users to reconcile code-base and user requirements.
Graduate Student Assistant
May 2019 – Jul 2019
Los Alamos National Laboratory, Los Alamos, NM
Built ML models to quantify experimental error and detect outliers in nuclear cross section data using measurement features and covariances. Results published in Nuclear Instruments and Methods in Physics Research A.
Boilers and Turbines Operator
Jun 2015 – Jun 2018
NRG Energy Power Station, Middletown, CT
Operated, tested, and maintained condensate, feedwater, hydrogen, nitrogen, and fuel oil systems under plant operating procedures.
Education
PhD, Mechanical and Aerospace Engineering
Jan 2025
University of Notre Dame, Notre Dame, IN
MS, Mechanical and Aerospace Engineering
May 2022
University of Notre Dame, Notre Dame, IN
BS, Nuclear Engineering
Dec 2017
Thomas Edison State University, Trenton, NJ
AS, Nuclear Engineering
May 2015
Three Rivers Community College, Norwich, CT
Awards and service
Nicholas C. Metropolis Postdoctoral Fellowship, Los Alamos National Laboratory.
Conference Paper Award, 2025 ANS Mathematics and Computational Methods conference.
Session Chair, Machine Learning and Artificial Intelligence I and IV, 2025 International Conference on Mathematics and Computational Methods Applied to Nuclear Science and Engineering.
Reviewer, Annals of Nuclear Energy and ANS Mathematics and Computation Division (2025–present); Nuclear Science and Engineering (2026–present).
Volunteer judge, Los Alamos National Laboratory 2025 Annual Student Symposium.
Single Grid Error Estimation for Neutron Transport Solvers. Ben Whewell and Ryan G. McClarren, (2025). Journal of Verification, Validation and Uncertainty Quantification. 10(2): 021001. DOI: 10.1115/1.4069426
Collision-Based Hybrid Method for Two-Dimensional Neutron Transport Problems. Ben Whewell and Ryan G. McClarren, (2025). Nuclear Science and Engineering, 1-23. DOI: 10.1080/00295639.2025.2489778
Multigroup Neutron Transport Using a Collision-Based Hybrid Method. Ben Whewell, Ryan G. McClarren, Cory D. Hauck, and Minwoo Shin, (2023). Nuclear Science and Engineering, 197:7, 1386-1405. DOI: 10.1080/00295639.2022.2154119
A low-rank power iteration scheme for neutron transport criticality problems. Jonas Kusch, Benjamin Whewell, Ryan McClarren, and Martin Frank, (2022). Journal of Computational Physics, 470, 111587. DOI: 10.1016/j.jcp.2022.111587
Data Reduction in Deterministic Neutron Transport Calculations Using Machine Learning. Ben Whewell and Ryan G. McClarren, (2022). Annals of Nuclear Energy, 176, p. 109276. DOI: 10.1016/j.anucene.2022.109276
Evaluating 239Pu(n,f) cross sections via machine learning using experimental data, covariances, and measurement features. B. Whewell, M. Grosskopf, and D. Neudecker, (2020). Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors, and Associated Equipment, 978, p. 164305. DOI: 10.1016/j.nima.2020.164305
