# Gaurav Sawant

Gaurav Sawant is a remote worker on Himalayas, Junior AI/ML Engineer at The Unmarketing Agency, based in India.

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

```text
AI/ML engineer specializing in applied NLP, multimodal systems, and RAG pipelines to ship production-ready models.
```

| Detail | Value |
| --- | --- |
| Availability | Open to opportunities |
| Location | India |
| Authorized to work in | India |
| Job categories | AI ML Engineer, Machine Learning Engineer, NLP Engineer, Computer Vision Engineer, Data Scientist, AI ML Software Engineer, AI ML Engineering Jobs, AI Engineer, AI ML Engineer |
| Skills | Python, NumPy, Pandas, TensorFlow, PyTorch, Keras, SQL, Git, Docker, AWS, Machine Learning, Deep Learning, NLP, LLM, RAG, Hugging Face, fastAPI, MLFlow, Prompt Engineering, Vision Language Models, YOLOv8, EfficientNetB0, Isolation Forest, Random Forest, XGBoost, Faiss, BM25, Qdrant, Redis, LoRAs, PEFT, Ragas, Langfuse, Reciprocal Rank Fusion, Chi, Lang Chain, Temporal |

## What I'm looking for

```text
I’m looking for a role where I can build and deploy production NLP/ML systems—especially RAG and multimodal pipelines—while owning evaluation and observability end to end, with room to grow into senior problem-solver ownership.
```

## About

```text
I’m an AI/ML Engineer with 1.5 years of experience in applied Machine Learning, Deep Learning, NLP, and multimodal systems—especially LLM fine-tuning and RAG pipelines. I publish research in Computer Vision and NLP, and I’m driven by building end-to-end AI solutions from research to deployment.

At The Unmarketing Agency, I built a multimodal Text Suggestion Engine using Vision-Language Models to generate titles, descriptions, and SEO tags from product images—reducing manual listing effort. I also implemented a hybrid search system (BM25 + semantic embeddings with FAISS) with tag-based filtering to improve search relevance.

On the computer vision side, I designed a two-stage pipeline combining YOLOv8 object detection with EfficientNetB0 classification, achieving 94% accuracy on 2000+ custom-annotated images for state condition identification. I additionally implemented an automated image quality validation pipeline so only compliant images flow downstream.

Earlier at Claysys Technologies, I developed a bank transaction fraud detection POC using a hybrid unsupervised/anomaly + sequential learning approach (Isolation Forest, Autoencoders, LSTM feature extraction) feeding Random Forest and XGBoost. In parallel, my projects like DocuMind and YTResponder strengthened my focus on evaluation, observability, and practical system design.
```

## Experience

### Junior AI/ML Engineer (current)

The Unmarketing Agency. Dec 2025 - Present

```text
Built a multimodal text suggestion engine using vision-language models to generate product titles, descriptions, and SEO tags from images, reducing manual listing effort. Developed a BM25 + FAISS hybrid search with tag-based filtering and implemented a two-stage CV pipeline (YOLOv8 + EfficientNetB0) achieving 94% accuracy on 2000+ custom-annotated images.
```

Skills: Vision-Language-Models, BM25, Faiss, YOLOv8, EfficientNetB0, Image-Preprocessing-Validation

### AI/ML Engineer - L1

Claysys Technologies. Jul 2025 - Dec 2025

```text
Developed a bank transaction fraud detection POC combining unsupervised anomaly detection (Isolation Forest, autoencoders) with LSTM-based feature extraction feeding an ensemble of Random Forest and XGBoost. Engineered temporal and historical features on a synthetic transaction dataset to simulate realistic customer spending behaviors and transaction sequences.
```

Skills: Fraud-Detection, Anomaly-Detection, Isolation-Forest, Synthetic-Data-Generation, Random-Forest, XGBoost

## Education

### Goa University

Master of Science in Data Science, Data Science. 2023 - 2025. Grade: CGPA: 9.5

```text
Master of Science in Data Science at Goa University (CGPA: 9.5).
```

### Goa University

Bachelor of Science in Data Science, Data Science. 2020 - 2023. Grade: CGPA: 9.34

```text
Bachelor of Science in Data Science at Goa University (CGPA: 9.34).
```

## Tech stack

- NumPy
- Pandas
- Gmail
- Redis
- TensorFlow
- PyTorch
- MLflow
- Keras
- FastAPI
- SQL
- XGBoost
- Hugging Face
- Temporal
- Qdrant
- LangChain
- Langfuse
- Score
- Chi
- Ragas
- Enhance
- Faiss
- PEFT
- Remote

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

## People also viewed

- [Spartian User](https://himalayas.app/@spartianuser): AI & ML Intern, Edunet Foundation
- [Atish Sanap](https://himalayas.app/@atishsanap): ML Engineer, Unified Mentor
- [abhinav sharma](https://himalayas.app/@abhinavsharma6): ML Researcher, Personal Projects
- [NIRMAL KUMAR](https://himalayas.app/@nirmalkumar1): AI/ML Engineer, Beshak.org
- [Shiv Sunder](https://himalayas.app/@shivsunder): Machine Learning Intern, Quantiphi
- [Varshith Gaddam](https://himalayas.app/@varshithgaddam): AI/ML Engineer Intern, US Based Client Project
- [Sai Kiran](https://himalayas.app/@saikiran14): ML Engineering Intern, Google Partner Project
- [Yugendra Ratna](https://himalayas.app/@yugendraratna): AI/ML Engineer, Ignatiuz
- [Manoj Sivaraj](https://himalayas.app/@manojsivaraj): Associate Product Engineer, Temenos India Private Limited
- [Yash Gaikwad](https://himalayas.app/@yashgaikwad1): Software Engineer – AI/ML, Prama India Pvt Ltd
