Phase field dislocation dynamics study of grain boundary-dislocation interactions
B. Murgas, A. Mishra, N. Mathew, and A. Hunter
Journal of Applied Physics 139, 155101
Hello, I am Avanish Mishra
Staff Scientist at Los Alamos National Laboratory — integrating first-principles methods and molecular dynamics with machine learning and quantum computing to accelerate materials discovery
Atomistic to continuum
AI/ML-driven discovery
For chemistry & materials
Simulation ↔ experiment
I am a staff scientist in the Theoretical Division at Los Alamos National Laboratory, specializing in the design of structural materials for extreme environments and functional materials for energy-to-electronics applications.
My work integrates first-principles methods (DFT, VASP, Quantum ESPRESSO) and molecular dynamics (LAMMPS) with emerging paradigms such as machine learning — including graph neural networks, generative AI, active learning, and large language models — and quantum computing (Qiskit, pySCF) to accelerate materials discovery.
I have contributed to open data infrastructure (aNANt database, JARVIS-Leaderboard, URSA) and authored 38+ peer-reviewed publications with 2,538+ citations and an h-index of 19.
Ph.D. Materials Science
Indian Institute of Science, Bangalore
(2014–2019)
M.Sc. Physics · B.Sc. Physics, Math & Chemistry — DDU Gorakhpur University
Director's Postdoc Fellow — LANL, 2022
Science in 3 (Top 30 postdocs) · Kawazoe Prize · GATE AIR 36 · CSIR-NET AIR 58
DFT · MD · VASP · LAMMPS · Quantum ESPRESSO
pySCF · Qiskit · ASE · GenAI · LLMs · Agentic AI
TMS · APS · MRS · ICME
Symposium co-organizer: TMS 2025 & 2026 AI-ICME
Leading research in materials informatics, quantum computing for chemistry, generative AI for process-structure mapping, and virtual characterization tools.
Developed physics-informed ML for grain boundary property prediction using strain functional descriptors. Selected as one of 30 postdocs for "Science in 3" at LANL.
Pioneered virtual characterization tools for shock-induced deformations, phase transformation mechanisms, and diffraction fingerprinting in dynamic loading.
Dissertation: "Exploration of exfoliation, functionalization and properties of MXenes via first-principles and machine learning."
Our interdisciplinary team at Los Alamos National Laboratory
Staff Scientist, Theoretical Division, LANL
04/2026 - present
08/2025 - present
Co-advised with Dr. Yu Zhang, LANL
06/2026 - present
Carnegie Mellon University
Co-advised with Dr. Saryu Fensin, LANL
06/2026 - present
Purdue University
Leveraging artificial intelligence, machine learning, and quantum computing to solve the hardest problems in materials science
Data-driven discovery fusing physics-based descriptors with ML models. Active learning, graph neural networks, and explainable AI for accelerated materials design.
Learn more →Hybrid quantum–classical strategies for correlated materials. Variational algorithms, error mitigation, and domain-specific workflows for catalysis and energy storage.
Learn more →Predictive models for extreme environments — fusion reactors, shock deformation, and radiation damage. Multiscale simulations from atoms to continuum.
Learn more →Engineering materials from bulk to 2D — complex oxides, heterostructures, and hybrids for energy, electronics, and photonics.
Learn more →Computational tools for texture analysis, diffraction simulation, and orientation relationships from atomistic data.
Learn more →A selection of recent contributions to AI-driven materials science
Showing curated papers from CV. Use DOI Search for live Crossref lookup.
B. Murgas, A. Mishra, N. Mathew, and A. Hunter
Journal of Applied Physics 139, 155101
A. Mishra, J. S. Carpenter, and S. J. Fensin
In press
A. Mishra, B. W. Hamilton, M. S. Nitol, N. Mathew, T. C. Germann, and S. J. Fensin
ICCV Workshops, 3593-3602
K. Dang, S. Suresh, A. Mishra, I. Chesser, N. Mathew, E. M. Kober, and S. J. Fensin
Scientific Data 12, 955
A. Mishra, S. Suresh, S. J. Fensin, E. M. Kober, and N. Mathew
Physical Review Materials 8, 123605
A. C. Rajan, A. Mishra, S. Satsangi, R. Vaish, H. Mizuseki, K.-R. Lee, and A. K. Singh
Chemistry of Materials 30, 4031
Codes, databases, and AI-powered tools I've developed and contributed to
India's first computational materials database — 23,000+ MXenes with optimized structures and electronic properties for ML training.
Database · ML-Ready · Ph.D.Python package for virtual texture analysis from atomistic microstructures: orientation relationships, misorientations, Schmid factors.
Python · AnalysisOfficial contributor to NIST's benchmarking platform for materials science ML methods and AI models.
NIST · AI BenchmarkingContributor to LANL's Universal Research and Scientific Agent — an AI-powered research assistant for scientific discovery.
LANL · LLM AgentWe are actively recruiting motivated researchers at all levels who are passionate about AI, quantum computing, and materials science
Send your CV and a brief statement of research interests.
Work at the forefront of AI + materials science at one of the world's premier research laboratories. Our group offers a unique combination of cutting-edge science, world-class computing resources, and a collaborative, mentorship-driven environment.
Access to LANL supercomputers & quantum hardware
AI, quantum computing, physics & chemistry
Mentorship & pathways for future growth
Located in beautiful Northern New Mexico
Open to Non-sensitive Foreign Nationals, Permanent Residents, and US Citizens.
Interested in collaboration or open positions?