Rajeev Jain

Research Software Engineer | ML Infrastructure | Scientific Computing

Rajeev Jain

I build research software for climate analysis, AI workflows, and large simulation codes at Argonne National Laboratory, with a joint appointment at the University of Chicago.

My work sits where scientific computing meets usable engineering: climate and mesh analysis, machine-learning infrastructure, high-performance I/O, and tools that researchers can actually extend. I care most about software that survives beyond a single project cycle.

Google Scholar · ORCID

Argonne National Laboratory · University of Chicago · Climate, HPC, and AI systems

Featured systems work

AI weather modeling on Aurora

Porting and stabilizing large weather-model training workflows on Intel GPUs, with attention to portability, runtime behavior, and scientific throughput.

Open-source climate tooling

UXarray

Mesh-aware analysis for next-generation climate grids, built so scientific users can inspect, subset, and reason about unstructured datasets without bespoke code for each mesh.

AI-agent workflows

Scientific MCP workflows

Natural-language dataset discovery, plotting, workflows, and remote execution for scientific analysis across local machines and HPC systems.

Selected work

Selected projects

Representative work across climate science, cancer AI, and simulation software.

Lead developer | Open-source climate analysis | Documentation

UXarray

Python library for unstructured climate grid analysis used by DOE labs, NCAR, and universities working with MPAS, ICON, SAM, and other next-generation meshes.

Technical article · UXarray MCP server

Aurora exascale system | Argonne Leadership Computing Facility

Pangu-Weather on Aurora

PyTorch-based reimplementation of Pangu-Weather using the Spectral Fourier Neural Operator for deployment on more than 60,000 Intel GPUs.

  • Ported the workflow to Intel GPUs and ran it at large scale on Aurora.
  • Contributed to DOE exascale work in Earth system modeling and forecasting.

Technical article

Core contributor | Cancer AI benchmarking infrastructure

CANDLE / IMPROVE

Hyperparameter optimization and benchmarking infrastructure for cancer drug response models at supercomputer scale.

  • Ran more than 10,000 training experiments across Summit, Theta, and Cori.
  • Built GitHub Actions workflows for cross-study validation in a 15+ researcher collaboration.
  • Published in Briefings in Bioinformatics in 2025.

I/O and compression work for multiphysics simulation

FLASH-X

Optimization of checkpoint and restart workflows for a million-line multiphysics simulation engine used in astrophysics, combustion, and fluid dynamics.

  • Implemented asynchronous HDF5 I/O with Argobots plus SZ3 and ZFP compression.
  • Reduced checkpoint overhead by 40-70% on Summit and delivered 50%+ storage savings.
  • Enabled cross-checkpoint restart between AMReX and Paramesh solvers.

DOE NEAMS, 2009-2016

MeshKit

Open-source C++ toolkit for automated nuclear reactor core mesh generation and lattice hierarchy modeling.

  • Led the design of parallel meshing and multi-format I/O for reactor simulation teams at Argonne.
  • Won Best Paper Award at the International Meshing Roundtable in 2010.

Technical expertise

Capabilities across scientific software and systems

A compact view of the engineering areas I work in most often, from ML and analysis pipelines to HPC runtime and open-source delivery.

Scientific Python and ML

Data, models, and analysis workflows

  • PyTorch, TensorFlow, NumPy, Pandas, Xarray, and Scikit-learn for model development and scientific analysis.
  • Parsl and Swift/T for large experiment campaigns and repeatable workflow execution.

HPC systems and storage

Performance, portability, and I/O

  • MPI, OpenMP, HDF5, NetCDF, MOAB, and storage-aware design for leadership-class machines.
  • Intel GPUs, CUDA portability, asynchronous checkpoint workflows, and runtime debugging on shared systems.

Open-source delivery

Software other researchers can extend

  • Release engineering, CI pipelines, testing, and packaging for long-lived scientific projects.
  • Roadmap ownership, collaboration across labs and universities, and mentoring around sustainable engineering practice.

Scientific domains

Problem-driven engineering

  • Climate modeling, unstructured mesh analysis, cancer pharmacogenomics, computational physics, and simulation software.
  • AI infrastructure and reproducible workflows built around domain constraints rather than generic demos.

Publications and talks

Selected papers, workshops, and presentations

More than 22 publications across HPC, machine learning, and computational science.

Recognition

Recognition and service

Awards, funding, and community work related to the software and collaborations above.

Work authorization

U.S. Permanent Resident

Authorized to work in the United States without sponsorship.

R&D 100 | 2023

CANDLE

Project recognized by R&D World in 2023.

R&D 100 | 2022

FLASH-X

Project recognized by R&D World in 2022.

Training and technical distinction

ATPESC Scholar

Selected in 2015 for Argonne's training program on extreme-scale computing.

Research publication

Best Paper Award

International Meshing Roundtable, 2010, for automated reactor core mesh generation research.

Research funding

  • DOE SEATS Active Software Ecosystem for Advancing Climate Tools and Services.
  • NSF Raijin Active Collaborative research in climate model analysis.
  • DOE ECP CANDLE Core contributor from 2017 to 2023.
  • DOE NEAMS Principal investigator for MeshKit from 2009 to 2016.

Service and mentorship

  • SBIR/STTR Proposal Reviewer U.S. Department of Energy.
  • Panelist 5th Infraday Midwest Event on public infrastructure and AI.
  • Reviewer Journal of Open Research Software and NumGrid.
  • Committee Member NumGrid 2020 Program Committee.

Mentored students and doctoral researchers on scientific Python, HPC techniques, and open-source development practices.

Background

Roles, education, and collaboration style

Research roles across labs and universities, centered on long-lived software and collaborative delivery.

Roles

2009-present

Argonne National Laboratory

Principal Specialist in Research Software Engineering, working across UXarray, FLASH-X, CANDLE/IMPROVE, MeshKit, and urban simulation software efforts.

2023-present

University of Chicago

Staff At-Large with joint research activity spanning cancer pharmacogenomics and Earth system science.

2007-2009

Arizona State University

Research and teaching assistant in structural and computational mechanics, focused on blast mitigation and FEM-based design optimization.

Education

  • M.S. Computer Science University of Chicago, 2020
  • M.S. Structural Engineering Arizona State University, 2009
  • B.Tech. Mechanical Engineering IIT ISM Dhanbad, 2006