BANOTH JAGADISH

Available to hire

I’m Banoth Jagadish, an AI/ML-focused B.Tech IT undergraduate at NIT Srinagar with research experience from NITK Surathkal.

About

I’m Banoth Jagadish, an AI/ML-focused B.Tech IT undergraduate at NIT Srinagar with research experience from NITK Surathkal. I enjoy building transformer-based NLP systems—especially neural machine translation—and developing practical generative AI pipelines that can retrieve, reason, and produce grounded answers.

In my projects, I’ve worked on agentic multimodal RAG workflows (handling text, PDF, images, and audio/video via chunking, OCR, captioning, and transcription) and created auditable LLM decision pipelines with testing and confidence-based fallbacks. I’m comfortable with PyTorch and Hugging Face, LoRA fine-tuning, hybrid retrieval (dense + BM25 + reranking), and designing reproducible evaluations.

  • Joined October 2026

Languages

  • EnglishAdvanced
  • HindiIntermediate

Industry experience

  • Computers & Electronics
  • Software & Internet
  • Education
  • Professional Services

More experts in Srinagar, India

Projects · 3

The project

A simulation that explores how an AI recommendation can sit inside an inspectable, rule-based workflow. Demonstration data represents synthetic payment records; actions are simulated.

What I built

  • Bounded AI classification with schema validation and a deterministic fallback.
  • Versioned policy rules, retry limits, stopping rules and human escalation.
  • Append-only audit logging, batch evaluation and automated tests.
  • A simple interface for inspecting decisions and outcomes.

Relevant client work

Python workflow prototypes, validation, auditability, error handling and repeatable testing before connecting live systems.

Tools: Python, pytest, Streamlit and LLM classification.

[Review the source code, tests and documentation](https://www.twine.net/signin

RecoverAI: auditable AI decision workflow simulation
  • AI Developer

The project

A low-resource machine translation portfolio project for English-to-Kashmiri text.

What I built

  • A multilingual NLLB-200 translation workflow with a parameter-efficient LoRA adapter.
  • Reusable single-input and batch inference scripts.
  • Model and adapter loading with CPU/GPU device selection.
  • Published adapter artifacts for reproducible experimentation.

Relevant client work

Hugging Face inference integration, adapter loading, multilingual NLP experiments and fine-tuning support.

Tools: Python, PyTorch, Hugging Face Transformers, NLLB-200 and LoRA.

[View the project code](https://www.twine.net/signin

[View the published LoRA adapter](https://www.twine.net/signin

Source code, reusable inference scripts and model artifacts are available for review.

English-to-Kashmiri translation with NLLB-200 and LoRA
  • AI Developer

The project

A portfolio/research prototype for document-grounded question answering across mixed input formats.

What I built

  • A modular Python pipeline separating ingestion, retrieval, generation, verification and evaluation.
  • Dense and BM25 retrieval with reranking to assemble relevant context.
  • Citation and evidence checks, with confidence-based retry or abstention paths.
  • Evaluation scripts and documentation so individual pipeline stages can be inspected and improved.

Relevant client work

Document search, knowledge assistants, retrieval debugging and a focused RAG proof of concept.

Tools: Python, FAISS, BM25, Hugging Face Transformers and LLM workflows.

[View source code and documentation](https://www.twine.net/signin

This is a portfolio prototype; its documented evaluation includes limitations.

Document Q&A with hybrid retrieval and evidence checks
  • AI Developer

Work experience

AI/ML Intern · Centre for System Design, NITK SurathkalDec 2025 – Feb 2026 · 3 mos

Developed Python-based ML workflows for data processing, model experimentation and computational problem-solving in a research environment. Applied reproducible experimentation, structured evaluation, debugging and technical documentation. Internship: December 2025–February 2026.

Education

B.Tech in Information Technology (in progress) · National Institute of Technology Srinagar2024 – 2026

Currently pursuing B.Tech in Information Technology. Started August 2024; the degree is ongoing and no graduation date is claimed.

Hire BANOTH JAGADISH today

Post a job and invite BANOTH, or contact them directly. No hidden commission.

Post a job