AI Research Intern @ ABB · Previously DFKI

Vishal Banwari

Human in the loop. Code in the wild.

MSc Computer Science @ RPTU Kaiserslautern · Intelligent Systems

0 Publications
0 Projects
0 Yrs Exp.

Who I Am

Based in Kaiserslautern, Germany
Currently AI Research Intern @ ABB
Studying MSc Computer Science · RPTU
Research focus NLP · Human-AI · LLMs
Background Software Engineer → AI Researcher
Vishal by a lake in nature

I'm pursuing my MSc in Computer Science at RPTU Kaiserslautern, specializing in Intelligent Systems. I'm currently an AI Research Intern at ABB, where I apply LLMs to industrial fault diagnosis and build RAG pipelines for log intelligence. Before pivoting to research in 2024, I spent seven years shipping software in C++, C#, and Angular across industrial sectors — which gave me a strong intuition for what AI actually needs to work in the real world.

My research sits at the intersection of human-in-the-loop learning, large language models, and AI sustainability. I care deeply about the gap between what AI can do and how humans actually work with it. My published work covers the energy footprint of LLM APIs and web agents, and a framework called HILL that lets humans directly reshape how a model learns during training.

Human-centered AI LLM research Sustainable ML Industrial applications Open research

Featured Work

6 featured projects spanning LLM, Computer Vision, and Research.

Experience

From industrial software engineering to AI research — 7+ years building systems that matter.

Jan 2026 – Present
● Active

AI Research Intern

ABB · Industry / Kaiserslautern, Germany
  • Building root cause analysis for logs using LLMs
  • Developing RAG pipelines and Streamlit interfaces for log intelligence
  • Applying LLM-based reasoning to industrial fault diagnosis workflows
LLMsRAGStreamlitLog Analysis
Apr 2024 – Dec 2025
~1.5 yrs

Research Assistant

DFKI · Research / Kaiserslautern, Germany
  • Developed Python GUI tools for human-in-the-loop ML workflows
  • Created novel loss functions with real-time feedback signals
  • Built visualizations for model confidence & embedding insights
  • LLMs and AI Agents energy consumption & efficiency benchmarking
PythonPyTorchHuman-AIVisualization
Jun 2021 – Feb 2023
~2 yrs

Senior Engineer

Rugged Monitoring · Industry / Hyderabad, India
  • Full-stack product development using Angular + .NET Core
  • Designed and delivered industrial monitoring dashboards
  • Led backend architecture for smart data analytics features
Angular.NET CoreFull-StackAnalytics
Feb 2017 – May 2021
~4 yrs

Software Engineer

Qualitrol · Industry / Ahmedabad, India
  • Built WPF desktop applications using C++/C#
  • Integrated ML modules for energy sector systems
  • Enhanced UI/UX for electrical data visualization tools
C++C#WPFML Integration

Publications

01 arXiv · 2025

This Is Taking Too Long — Time as a Proxy for LLM Energy Consumption

LLM energyInference timeAPI
02 AAAI · 2025

Sustainable Web Agents: Benchmarking Energy Consumption

Web agentsCO₂Sustainability
03 HHAI · 2025

HILL: Interactively Guiding Model Training Through Human Intuition

Human-in-loopLatent spaceDistillation

Tech Stack

The synapses that power my work.

💬

Languages

Python C++ C# JavaScript SQL HTML/CSS
🧪

ML / AI & NLP

PyTorch TensorFlow Hugging Face LangChain scikit-learn OpenCV LoRA / PEFT RAG Sentence Transformers
🌐

Web & Tools

Angular .NET Core Streamlit Gradio Git Docker Linux WPF
🚀

Focus Areas

Generative AI NLP Computer Vision Deep Learning Human-AI Collaboration Continual Learning RAG Systems AI Sustainability

Beyond Code

🎸Guitar
🏓Table Tennis
📚Reading
🏃Running
💪Gym
⛰️Hiking
♟️Chess
🎹Piano
🌱Gardening

Let's Build Something Together

Whether it's a research collaboration, engineering challenge, or just a conversation about AI — I'd love to hear from you.