Dr. Mohammad Soleymanibrojeni

AI Research Engineer

Intelligent solutions for digital transformation

About Me

Multidisciplinary materials engineer with 8+ years of research and industry experience, specializing in AI/ML solutions. An innovative thinker who integrates emerging technologies to drive continuous improvement and accelerate process timelines. Results-driven professional with expertise in materials properties, big data analytics, forecasting, visualization, technical reporting, agentic workflows, and collaboration. Exceptionally dedicated, with strong interpersonal, communication, and organizational skills.

Areas of Expertise

AI/ML Research

  • Active Learning Models
  • Battery Interface Prediction
  • Generative AI Pipelines
  • Semantic Interfacing
  • Knowledge Graphs
  • Adaptive Data Structures

Materials Engineering

  • Battery Materials
  • Materials Selection
  • Failure Analysis
  • Technical Standards
  • Quality Assurance
  • Materials Characterization

Technical Development

  • Research Toolbox Creation
  • Automated Debugging Systems
  • Novel Retrieval Systems
  • Publication Assistance Tools
  • Agentic Workflows
  • Data Modeling

Tech Stack

  • Python
  • PyTorch
  • FastAPI
  • Docker/Containerization
  • CI/CD
  • React/Next.js

Data & Analytics

  • Big Data Analytics
  • Forecasting
  • Visualization
  • Technical Reporting
  • Systemic Analysis
  • Cloud Deployment

Collaboration

  • International Partnerships
  • Multi-million Euro Initiatives
  • Technical Advisory
  • Documentation
  • Workflow Coordination
  • Cross-functional Leadership

Featured Projects

1
Research
2022 - 2024

Active Learning for Battery Interface Prediction

Developed an innovative active learning approach to model solid-electrolyte interphase formation in Li-ion batteries, achieving 90%+ prediction accuracy while minimizing computational costs.

Technologies Used

PyTorchPythonActive LearningGaussian ProcessBayesian Statistics

📄 Related Publication

An active learning approach to model solid-electrolyte interphase formation in Li-ion batteries (2024) - 5 citations

Impact

  • Reduced experimental iterations by 70%
  • Achieved 90%+ prediction accuracy
  • Published in Journal of Materials Chemistry A
2
Tool
2021 - 2023

ML-Powered Research Toolbox

Collaborated on the creation of a comprehensive machine learning toolbox for materials research that dramatically accelerated analytical processes from hours to minutes.

Technologies Used

PythonFastAPIDockerCI/CDPyTorch

Impact

  • Analysis time reduced by 85%
  • Adopted by multiple research groups
  • Integrated into BIG-MAP project workflow
3
Method
2022 - Present

Generative AI Pipeline for Materials Discovery

An Agentic AI approach that synergizes large language models (LLMs) with a domain-specific knowledge graph to enhance reasoning and autonomy in generating, submitting, and monitoring simulation protocols for materials discovery.

Technologies Used

PyTorchAgentic AIPythonHigh-Performance ComputingKnowledge GraphsQuantum Espresso

Impact

  • Contributed to BIG-MAP €20M research initiative
  • Automated DFT protocol generation and validation
  • Reduced discovery timeline by 60%
4
Tool
2023 - Present

tex-Rex: AI-Powered Publication Assistant

Tex-Rex is an AI-powered academic paper analysis tool that helps researchers improve their scientific manuscripts through automated feedback and suggestions.

Technologies Used

PythonNLPLLMs

Impact

  • Reduced publication preparation time by 40%
  • Supported multiple languages
  • Improved consistency across research publications
5
Method
2022 - 2023

Elastic Dictionary for Materials Data

An adaptive, hierarchical data structure that dynamically organizes string data and text into a semantic tree structure.

Technologies Used

PythonKnowledge GraphsNLPDatabase DesignReact

Impact

  • Improved data retrieval efficiency by 65%
  • Enhanced cross-referencing of research data
  • Integrated with multiple research databases
6
Research
2019 - 2020

Atomistic Simulation of Material Interfaces

Conducted comprehensive atomistic simulations of epoxy/water/aluminum systems using the ReaxFF method to understand interface behavior at the molecular level.

Technologies Used

ReaxFFMolecular DynamicsPythonHigh-Performance Computing

📄 Related Publication

Atomistic simulations of Epoxy/Water/Aluminum systems using the ReaxFF method (2020) - 14 citations

Impact

  • Published in Computational Materials Science
  • Cited by 14+ research papers
  • Provided insights for corrosion prevention

Publications

9
Publications
120
Citations
6
Years
13
Citations per Paper

Timeline

An active learning approach to model solid-electrolyte interphase formation in Li-ion batteries

M Soleymanibrojeni, CRC Rego, M Esmaeilpour, W Wenzel

Journal of Materials Chemistry A 12 (4), 2249-2266

This paper presents an innovative active learning approach for modeling the formation of solid-electrolyte interfaces in lithium-ion batteries, significantly improving prediction accuracy and computational efficiency.

📚5 citations

Surface energies control the anisotropic growth of β-Ni (OH) 2 nanoparticles in stirred reactors

N Streichhan, D Goonetilleke, H Li, M Soleymanibrojeni, PW Hoffrogge, et al.

Surfaces and Interfaces 51, 104736

This study investigates how surface energies influence the anisotropic growth of β-Ni(OH)2 nanoparticles in stirred reactor environments, providing insights for controlled nanoparticle synthesis.

📚0 citations

Professional Experience

AI Research Engineer/Post-Doc

Karlsruher Institut für Technologie

November 2021 – Present
Karlsruhe
  • Developed active learning models for battery interface prediction with 90%+ accuracy
  • Created ML-powered research toolbox that accelerated analytical processes
  • Implemented semantic interfacing and knowledge graphs for materials discovery
  • Collaborated with 30+ international partners on BIG-MAP (€20M research initiative)
  • Contributed to Plattform MaterialDigital (PMD) project development

Key Projects

  • Generative AI Pipelines for autonomous battery material discovery
  • Battery Interface Prediction with 90% accuracy
  • tex-Rex: AI-powered publication assistant
  • Elastic Dictionary: Adaptive data structure
Active LearningPyTorchPythonKnowledge GraphsNLPMaterials InformaticsAgentic AI

Materials Engineer

National South Fields Oil Company

March 2015 – August 2016
Ahvaz
  • Collaborated on materials selection for critical oil production equipment worth €10B+
  • Provided technical advisory across five departments to enhance operational efficiency
  • Partnered with teams to implement environmental/technical standards and compliance protocols
  • Worked cross-functionally to reduce material failure rates through systematic analyses
Materials SelectionTechnical StandardsFailure AnalysisQuality AssuranceCross-functional Collaboration

Education

Ph.D. in Materials Science and Engineering

Chinese Academy of Sciences

2021

Dissertation: Developed a novel method for characterizing aerospace materials

M.Sc. in Materials Science and Engineering

University of Tehran

2013

Thesis: Studied multi-scale finite element methods and atomistic models

B.Sc. in Materials Science and Engineering

Isfahan University of Technology

2011

Project: Investigated thermodynamic properties of materials

Get in Touch

Contact Information

Email

hi@moslmn.link

Location

Karlsruhe, Germany