Agniva Maiti

ML Engineer & NLP Researcher

I build machine learning systems for languages most AI ignores, and the apps that put them in people's hands.

Open to full-time software, ML and research roles, and freelance projects. Open to relocation.
More about me

About me

I'm a Computer Science graduate (B.Tech CSE, KIIT, 2026) working on NLP for low-resource Indian languages and on the software that puts it in people's hands. My research, mostly with RespAI Lab at KIIT, covers LLM and vision-language model fine-tuning (LoRA/QLoRA), machine translation and human-validated synthetic data, with papers at EMNLP 2025, WMT 2026 and GlobalSouthML at ICML 2026. I also built NagaNLP and NagaTranslate for Naga languages, and my Flutter app GScholar has passed 100,000 downloads on Google Play.

B.Tech in Computer Science and Engineering · Kalinga Institute of Industrial Technology (KIIT) · 2026 · CGPA 8.72/10

Publications

  1. EMNLP 2025 (Main Conference)

    Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval-Augmented Generation Across Learning Styles

    Debdeep Sanyal, Agniva Maiti, Umakanta Maharana, Dhruv Kumar, Ankur Mali, C. Lee Giles, Murari Mandal

  2. WMT 2026

    SCE-KIIT: Fine-Tuning NLLB-200 for English–Nagamese Translation

    Agniva Maiti, Aarsh Muley, Sovan Kumar Sahoo

  3. WMT 2026

    SCE-KIIT: KokLLaMA: Cross-Task Adaptation for Low-Resource English–Kokborok Translation

    Agniva Maiti, Aarsh Muley, Sovan Kumar Sahoo

  4. GlobalSouthML at ICML 2026 (poster)

    Bridging the Visual Gap: Resource-Efficient VLM Adaptation for Meitei Mayek using Synthetic Multi-Modal Mixtures

    Agniva Maiti, Aditya Tiwari, Dwarikanath Mahapatra, et al.

  5. GlobalSouthML at ICML 2026 (poster)

    Evaluating Indic Literary Creativity In LLMs through the Lens of the Shastras

    Agniva Maiti, Aarsh Muley, Aditya Tiwari, Dwarikanath Mahapatra, et al.

  6. arXiv preprint, 2025

    NagaNLP: Bootstrapping NLP for Low-Resource Nagamese Creole with Human-in-the-Loop Synthetic Data

    Agniva Maiti, Manya Pandey, Murari Mandal

What I do

Android & Flutter apps

Cross-platform and Android apps built with Flutter, Dart and Kotlin.

NLP, LLMs & ML

LLM fine-tuning (LoRA/QLoRA), machine translation, computer vision and on-device models, from data to working product.

Web apps

Modern web apps and sites with React and Next.js.

Featured projects

All projects

Experience

Full resume
  1. Aug 2026 - Sep 2026

    Speech Recognition (ASR) Engineer · Freelance

    Fine-tuned, aligned and benchmarked automatic speech recognition (ASR) models for Yiddish and Hebrew

  2. Feb 2025 - Jul 2025

    App Development Intern · DES Navalmal Firodia Law College (Agrovigya)

    Developed the Agrovigya Flutter app serving 36 districts, with quantized TensorFlow Lite models for offline use

  3. Dec 2024 - Jan 2025

    Research Intern, Dept. of Mathematics and Computing · IIT (ISM) Dhanbad

    Reviewed 20+ papers and reproduced and benchmarked 5+ state-of-the-art low-light enhancement models (e.g. Zero-DCE, DVN) using SSIM and PSNR

  4. May 2024 - Jul 2024

    Research Intern, Dept. of Artificial Intelligence · IIT Kharagpur

    Curated a benchmark of 18,700+ entries by aggregating and annotating Google and Bing results to analyze search engine bias

  5. Jan 2024 - Aug 2024

    Machine Learning Intern · RnPsoft Pvt Ltd

    Architected end-to-end ML inference pipelines for personalized educational media delivery, serving 500+ users

Let's work together

Hiring for a software, ML or research role, or have a freelance app, ML or NLP project in mind? I'm open to relocation and remote work, and I'd love to hear about it.