# PRATHAM YADAV

PRATHAM YADAV is a remote worker on Himalayas, AI Engineer Intern at Devkraft, based in India.

Source: https://himalayas.app/@prathamyadav2

```text
AI Engineer Intern at Devkraft fine-tuning a YOLO model for vehicle damage segmentation and automating assessment.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | India |
| Authorized to work in | India |
| Salary expectations | 70k+ INR |
| Job categories | AI Engineer, Machine Learning Engineer, Deep Learning Engineer |
| Skills | Generative AI, Machine Learning, Deep Learning, Computer Vision, Natural Language Processing, RAG, Agentic AI, LLM Fine tuning, LoRAs, QLoRA, Reinforcement Learning from Human Feedback, Instance segmentation, Multimodal Learning, Speech Recognition, predictive modeling |
| LinkedIn | https://linkedin.com/in/yppaarth |
| GitHub | https://github.com/yppaarth |

## About

```text
At Devkraft, I fine-tuned a YOLO-based instance segmentation model on custom datasets spanning eight vehicle damage classes. I also applied LoRA and QLoRA and developed a computer vision pipeline using PyTorch and OpenCV.

I implemented real-time inference and model deployment to automate vehicle damage assessment, reducing manual inspection effort by 80%. I also explored RLHF workflows to align model outputs with human preferences.

As an ML Engineer Intern at Samsung R&D, I developed a multimodal face-voice model for cross-lingual speaker recognition that achieved 28.46% EER and ranked in the top four. A two-stream architecture with gated fusion reduced model variance by 18%.

At Samsung ResearchLab, I built LW-DMNet, a lightweight CNN for dementia classification that achieved 98.73% accuracy with 90% fewer parameters. The work was published in Springer Lecture Notes in Networks and Systems, and received the Best Paper Award at the International Conference on Applied Artificial Intelligence (2AI2026).
```

## Experience

### AI Engineer Intern (current)

Devkraft. Sep 2026 - Present

```text
Fine-tuned a YOLO-based instance segmentation model on custom datasets for vehicle damage detection. Developed an end-to-end computer vision pipeline and implemented real-time inference, reducing manual inspection effort by 80%.
```

Skills: YOLO, Instance-segmentation, PyTorch, OpenCV, LoRAs, QLoRA, RLHF, Computer-Vision, Model-Deployment

### ML Engineer Intern

Samsung R&D. Jul 2025 - Jan 2026

```text
Developed a multimodal face-voice model for cross-lingual speaker recognition, achieving 28.46% EER and ranking top-4. Designed a two-stream deep learning architecture with gated fusion, reducing model variance by 18%.
```

Skills: Deep-Learning, Multimodal-Learning, Speech-Recognition, Gated-Fusion-Models, MLFlow, Ablation-Studies

### Research Assistant

Samsung Research Lab. Jul 2025 - Jan 2026

```text
Built LW-DMNet, a lightweight CNN for dementia classification, achieving 98.73% accuracy with 90% fewer parameters. Developed a multimodal CNN-BERT pipeline with gated attention fusion for Alzheimer's detection.
```

Skills: CNN, BERT, Gated-Attention, MLFlow, Pipeline-Engineering, Classification

## Education

### Delhi Technological University

M.Tech, Data Science. 2024 - Present. Grade: 8.12 CGPA

```text
Pursuing M.Tech in Data Science with a CGPA of 8.12.
```

### Ajay Kumar Garg Engineering College

B.Tech, Computer Science. 2020 - 2024. Grade: 7.15 CGPA

```text
Completed B.Tech in Computer Science with a CGPA of 7.15.
```

### Amazon

Amazon ML Summer School, Machine Learning

```text
Completed the Amazon ML Summer School program.
```

### DeepLearning.AI

Deep Learning Specialization, Deep Learning

```text
Completed the Deep Learning Specialization on Coursera.
```

### Stanford Online

Machine Learning Specialization, Machine Learning

```text
Completed the Machine Learning Specialization on Coursera.
```

### NVIDIA

Building RAG Agents with LLMs, LLMs

```text
Completed the Building RAG Agents with LLMs certification.
```

## Tech stack

- Postman
- Tableau
- Amazon S3
- GitHub
- Jenkins
- GitHub Actions
- Jupyter
- PySpark
- MySQL
- MongoDB
- OpenCV
- Python
- Java
- C++
- TensorFlow
- PyTorch
- MLflow
- scikit-learn
- Flask
- FastAPI
- Transformers
- Git
- Docker
- SQL
- XGBoost
- Hugging Face
- LightGBM
- LangChain
- Evidently AI
- Pinecone
- CrewAI
- GitHub Copilot
- N8N
- Faiss
- LangGraph
- LangSmith
- Optuna

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

## People also viewed

- [AGAMJOT CHOUDHARY (RA2311026010681)](https://himalayas.app/@agamjotchoudharyra23): iOS Student Developer, Apple & Infosys
- [Krisvarish User](https://himalayas.app/@krisvarish): AI Research Intern, Samsung
- [Dhruv Devaliya](https://himalayas.app/@dhruvdevaliya): Data Scientist Intern, NullClass
- [Akshay Jyani](https://himalayas.app/@akshayjyani): Machine Learning Engineer, Incept Labs
- [Tanish User](https://himalayas.app/@tanishuser1): Developer Intern, Samsung R&D Institute India
- [Himansh Sharma](https://himalayas.app/@himanshsharma1): AI / ML Intern, ASTRA AI
- [Siddharth Upl](https://himalayas.app/@siddharthupl): Chair, IEEE Computer Society Student Chapter, Mahindra University
- [Shukraditya Bose](https://himalayas.app/@shukradityabose): Machine Learning Engineer, Omli Kids Pvt. Ltd.
- [Kuladipkumar Joshi](https://himalayas.app/@kuladipkumarjoshi): Technical Lead (Individual Contributor), HCLTech
- [Nakul Sinha](https://himalayas.app/@nakulsinha): Student Researcher, Samsung SEED Lab