# Jitu Sahu

Jitu Sahu is a remote worker on Himalayas, Machine Learning Intern at National Institute of Technology, based in India.

Source: https://himalayas.app/@jitusahu

```text
Machine learning intern at National Institute of Technology who improved medical Q&A performance and safety with fine-tuned LLMs.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | India |
| Authorized to work in | India |
| Salary expectations | 70k+ INR |
| Job categories | Machine Learning Engineer |
| Skills | Machine Learning, Deep Learning, Transfer Learning, Natural Language Processing, Large Language Models, RAG, QLoRA, 4 Bit Quantization, Autoencoder, Convolutional Neural Networks, Stacked Cross Validation, TensorFlow, PyTorch, Qwen2.5 3B, VGG16 |

## About

```text
At National Institute of Technology, I applied transfer learning with pre-trained CNNs to 3,300 ISIC dermoscopy images. I also built an autoencoder-based model with classical classifiers and compared the CNN backbones, identifying VGG16 as the strongest feature extractor.

On my medical Q&A fine-tuning project, I raised ROUGE-L from 0.16 to 0.30 by fine-tuning Qwen2.5-3B with 4-bit QLoRA on deduplicated MedQuAD pairs. I also improved the safety-test pass rate from 3/12 to 12/12 using intent routing, fixed emergency replies, and a dose-number filter.

I added retrieval-augmented generation over NIH Q&As with a grounding check, blocking ungrounded medical terms in 7 of 50 answers. For my RAG Study Assistance project, I built a chatbot over course notes and past exam papers with cited answers and filtered retrieval.

I'm studying Computer Science and Engineering at GIET University. My work spans machine learning and language-model applications using Python, PyTorch, and TensorFlow.
```

## Experience

### Machine Learning Intern

National Institute of Technology

```text
Applied transfer learning with pre-trained CNNs on dermoscopy images and built an autoencoder-based model with stacked classifiers for lesion classification.
```

Skills: TensorFlow, Transfer-Learning, CNN, VGG16, VGG19, ResNet50, EfficientNet-B3, Autoencoder, Stacked-CV, Classification

## Education

### GIET University

Bachelor of Technology, Computer Science and Engineering. Grade: 8.08 CGPA

Activities and societies: Relevant Coursework: Operating Systems, Computer Networks, Cloud Computing, Object Oriented Programming, Data Structures and Algorithms

```text
Pursuing a Bachelor of Technology in Computer Science and Engineering with a CGPA of 8.08, expected to graduate in April 2026.
```

### Pragati Science Higher Secondary School

Honors Science Program, Science. Grade: 7.37 CGPA

```text
Completed Honors Science Program with a CGPA of 7.37 in May 2021.
```

## Tech stack

- Kubernetes
- Python
- Java
- Kotlin
- TensorFlow
- PyTorch
- Linux
- Shell
- Git
- Docker
- SQL
- LangChain
- Ollama
- Pinecone
- Groq
- Bash
- AWS

To contact Jitu, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Anubhav Agrawal](https://himalayas.app/@anubhavagrawal1): AI Engineer 2 , Griphic
- [Pramod Kumar M](https://himalayas.app/@pramod-kumar): Machine Learning Intern, Google AI ML Virtual Internship
- [Varada Vaidya](https://himalayas.app/@varadavaidya): Machine Learning Engineer, Independent Projects
- [Vasu M](https://himalayas.app/@vasum): Machine Learning Intern, VIT AP University
- [Shashvat Aghera](https://himalayas.app/@shashvataghera): AI/ML Intern, JA Assure
- [Dhruv Devaliya](https://himalayas.app/@dhruvdevaliya): Data Scientist Intern, NullClass
- [Sulaiman Ahmed](https://himalayas.app/@sulaimanahmed): Machine Learning Engineering Intern, FlyRank AI
- [Girija Awate](https://himalayas.app/@girijaawate): Research Intern Deep Learning & Medical Imaging, Indian Institute of Technology (IIT) Bombay
- [shiv narain](https://himalayas.app/@shivnarain): Research Intern, Indian Institute of Technology (IIT) Ropar
- [Lasya T P](https://himalayas.app/@lasyatp): AIML Intern, International Institute of Medical Science and Technology Co
