# Vatsalya Soni

Vatsalya Soni is a remote worker on Himalayas, AI Research Intern at Vansun Mediatech Private Limited, based in India.

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

```text
I build reliable agentic AI, RAG, and knowledge-graph systems that automate high-stakes workflows.
```

| Detail | Value |
| --- | --- |
| Availability | Open to opportunities |
| Location | India |
| Authorized to work in | India |
| Job categories | AI Engineer, AI Researcher, Machine Learning Engineer, Software Engineer, Data Engineer, Research Intern, Artificial Intelligence Engineer, AI ML Engineer, AI Engineering Specialist, AI Engineering, Artificial Intelligence Engineering, Python AI Engineer, AI Engineering Jobs |
| Skills | Python, SQL, C++, C, JavaScript, MCP, LangGraph, Temporal, Lang Chain, RAG, PEFT LoRA, Hugging Face, PyTorch, TensorFlow, scikit learn, Pandas, NumPy, Neuro Symbolic AI, NLP, Docker, Git, GitHub Actions, fastAPI, AWS, GCP, PostgreSQL, Neo4j, ChromaDB, Azure OpenAI, OCR, Knowledge Graphs, LLM Evaluation, LoRAs, Quantization, GitHub, Harness, Novel, Agentic AI, Black, Durable, PEFT |

## What I'm looking for

```text
I'm looking to build and research reliable AI systems, especially agentic workflows, RAG, LLM evaluation, and knowledge-graph-integrated applications with measurable real-world impact.
```

## About

```text
I've built agentic AI systems at Vansun Mediatech, including a six-agent creative-generation pipeline using LangGraph and Temporal that eliminated state-parity failures across orchestrated runs. I also deployed an Azure OpenAI-powered Meta Ads CPL watchdog on AWS EC2, reducing daily manual review time by approximately 97%.

As an AI research intern with the Artificial Intelligence Institute of South Carolina, I designed neurosymbolic architectures for Compact, Custom, and Composite AI Networks through enterprise Knowledge Graph integration. I co-authored three academic papers, including an IEEE-targeted article proposing a Symbolic-in-the-Loop execution gate for autonomous systems.

At Lattice Build Technology, I built a multimodal RAG pipeline for architectural PDFs and CAD assets that reduced retrieval latency by 35%, alongside an OCR-enabled Starling-7B data-entry system that improved extraction precision from 85% to 95%. My work spans LLM evaluation, RAG, fine-tuning, semantic retrieval, and production AI infrastructure.
```

## Experience

### AI Research Intern (current)

Vansun Mediatech Private Limited. Jun 2026 - Present

```text
Architected a 6-agent creative generation pipeline on LangGraph with Temporal durable execution, eliminating state-parity failures. Engineered an LLM-driven Meta Ads CPL watchdog with Azure OpenAI verdict scoring and one-click Slack execution, cutting daily manual review time by approximately 97%.
```

Skills: LangGraph, Temporal, Azure-OpenAI, Systemd, MCP, Python, LLM, Slack

### Research Intern

Artificial Intelligence Institute of South Carolina. Jul 2025 - May 2026

```text
Designed domain-specific neurosymbolic architectures for Compact, Custom, and Composite AI Networks (C3AN) via enterprise Knowledge Graph integration. Co-authored 3 high-impact academic papers including 2 comprehensive surveys and 1 IEEE-targeted article.
```

Skills: Neuro-Symbolic-AI, Knowledge-Graphs, Research, Academic-Writing, IEEE

### AI Engineer Intern

Lattice Build Technology Ltd.. Jun 2025 - Jul 2025

```text
Architected a multimodal RAG pipeline parsing complex architectural PDFs and CAD assets, driving a 35% reduction in data retrieval latency. Engineered a 45-field automated data-entry system on a fine-tuned Starling-7B LLM with integrated OCR, lifting extraction precision from 85% to 95% and cutting inference costs by 40%.
```

Skills: RAG, OCR, Starling-7B, Fine-Tuning, LLM, Data-Extraction, Python

## Education

### Delhi Technological University

Bachelor of Technology, Computer Science and Engineering. 2023 - 2027. Grade: 8.46

```text
Pursuing a B.Tech in Computer Science and Engineering with a CGPA of 8.46.
```

## Tech stack

- GitHub
- GitHub Actions
- NumPy
- Pandas
- PostgreSQL
- Neo4j
- JavaScript
- TensorFlow
- PyTorch
- scikit-learn
- FastAPI
- SQL
- Hugging Face
- Temporal
- LangChain
- ChromaDB
- Harness
- Black
- Agentic
- LangGraph
- PEFT
- Novel
- Durable
- X++

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

## People also viewed

- [Gunavathi R Bhat](https://himalayas.app/@gunavathirbhat): AI/ML Engineer, AIML TechnoSystems
- [Yash Kumar](https://himalayas.app/@yashkumar7): Founding AI Engineer, GeniOS
- [Siddh User](https://himalayas.app/@siddhuser): AI Engineer, Animeta AI
- [Sai Teja Meka](https://himalayas.app/@saitejameka): AI Engineer Intern, Cloud Bridge Solutions Inc
- [Shivain Singh](https://himalayas.app/@shivainsingh): AI Engineer, ZipExams
- [Harshit Vashisth](https://himalayas.app/@harshitvashisth): Data Science Intern, Medtek.ai
- [Samarth Singh](https://himalayas.app/@samarthsingh): AI/ML Applications Intern, AmberFlux EdgeAI Private Limited
- [Aryan Sivanandan](https://himalayas.app/@aryansivanandan): AI Engineer Intern, Applied AI Consulting (AAIC)
- [Chetan Pawar](https://himalayas.app/@chetanpawar): AI Engineer, Metalinked
- [Sreepallavi Manikonda](https://himalayas.app/@sreepallavimanikonda): Artificial Intelligence Intern, Flutura
