# Riya Singh

Riya Singh is a remote worker on Himalayas, Data Scientist at Miimansa AI, based in India.

Source: https://himalayas.app/@riyasingh18

```text
I build high-throughput document intelligence and machine learning systems.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | India |
| Authorized to work in | India |
| Salary expectations | 1127k+ INR |
| Job categories | Data Scientist, Machine Learning Engineer, Computer Vision Engineer, NLP Engineer |
| Skills | Python, C++, Pandas, NumPy, PyTorch, scikit learn, TensorFlow, Computer Vision, YOLO, OpenCV, Natural Language Processing, Document Intelligence, TROCR, DIT, Embeddings, RAG, Vector Search, Faiss, Hugging Face Transformers, fastAPI, Docker, Git, Streamlit, Cohere, Gemini, Pdf2image, PyPDF2, Regex, Plotly, Matplotlib, Random Forest, SVM, Feature Engineering, Hyperparameter Tuning |

## What I'm looking for

```text
I'm looking to build practical machine learning and document intelligence systems, especially in computer vision, NLP, RAG, and scalable model deployment.
```

## About

```text
At Miimansa AI, I fine-tune document intelligence models for medical workflows, achieving 95.8% accuracy on four-class medical document classification.

I optimized inference from 0.4 to 52 pages per second while removing LLM dependency and reducing inference cost. I also built a YOLO-based handwritten-versus-typed document routing layer that reaches 97% accuracy.

I develop end-to-end RAG and ML products, including a multimodal document intelligence system with hierarchical chunking, FAISS search, and a production-ready Streamlit interface. My clinical trial extraction pipeline uses chunking and embeddings to populate USDM JSON schemas.

I'm a Computer Science student at VIT Bhopal University and a Smart India Hackathon national finalist. I enjoy turning machine learning models into practical, scalable systems with measurable performance gains.
```

## Experience

### Data Scientist (current)

Miimansa AI. Oct 2025 - Present

```text
Fine-tuned a pretrained Microsoft DiT transformer for medical document classification, achieving 95.8% accuracy and optimizing inference throughput. Built a YOLO-based handwritten vs. typed document classifier and developed a clinical trial data extraction pipeline.
```

Skills: Microsoft-DX, YOLO, OpenCV, OCR, Document-Intelligence, Embeddings, RAG, fastAPI, Docker, Git

## Education

### VIT Bhopal University

B.Tech, Computer Science. 2022 - Present. Grade: 8.87

```text
Pursuing a B.Tech in Computer Science with a GPA of 8.87, expected to graduate in May 2026.
```

## Tech stack

- Cohere
- NumPy
- Pandas
- OpenCV
- Python
- C++
- TensorFlow
- PyTorch
- scikit-learn
- Streamlit
- FastAPI
- Gemini
- Git
- Docker
- Faiss
- Matplotlib

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

## People also viewed

- [Shubham Pandey](https://himalayas.app/@shubhampandey6): AI Engineer, Appinventiv Technologies
- [aksh modi](https://himalayas.app/@akshmodi): Cohort Participant & Contributor, MediaWiki Cohort 2 (Road to Wiki Tech)
- [Bhargav Reddy](https://himalayas.app/@bhargavreddy2): Machine Learning Intern, Intrust Innovation Labs
- [Onkar User](https://himalayas.app/@Onkar_Thete): Data Science Intern, Infyntrek Systèmes
- [Manish Rana](https://himalayas.app/@manishrana4): Data Science Intern, Sabudh Foundation
- [Madhuri Ghadge](https://himalayas.app/@madhurighadge): Project Intern, INBENNE
- [ANKIT SAH User](https://himalayas.app/@ankitsahuser): NLP Pipeline Developer, TimesPro (Campus Technology)
- [MD Shahzad](https://himalayas.app/@mohammedshahzad): Data Science with Gen AI Training, Vizztal Academy
- [Sulaiman Ahmed](https://himalayas.app/@sulaimanahmed): Machine Learning Engineering Intern, FlyRank AI
- [SK Shamim Aktar](https://himalayas.app/@skshamimaktar1): AI/ML Engineer, Salphan Energy Pvt. Ltd. (WIOX AI Solutions)
