# Deepanshu Yadav

Deepanshu Yadav is a remote worker on Himalayas, AI Research Intern at Indixpert Technology, based in India.

Source: https://himalayas.app/@deepanshuyadav1

```text
AI Research Intern building production RAG and real-time AI services with FastAPI on GCP.
```

| Detail | Value |
| --- | --- |
| Availability | Open to opportunities |
| Location | India |
| Authorized to work in | India |
| Job categories | AI Research Intern, Machine Learning Engineer, AI ML Engineer, Backend Engineer, Computer Vision Engineer, AI Research Internships, AI Intern, AI Internship, Artificial Intelligence Intern, AI ML Intern |
| Skills | AI Research, RAG Data Pipelines, Lang Chain, Pgvector, YOLO, PyTorch, scikit learn, Vertex AI, Cloud Run, Cloud SQL, Pub Sub, Cloud Storage, fastAPI, PostgreSQL, Docker, Git, Python, Java, SQL, OpenCV, Cloud IAM, Data Structures, Algorithms, Object Oriented Programming, Operating System, Gemini, GitHub, GROQ |
| Website | https://my-portfolio-9q9o.onrender.com |
| Portfolio | https://my-portfolio-9q9o.onrender.com |
| LinkedIn | https://www.linkedin.com/in/deepanshu-yadav-9a104321a |
| GitHub | https://https://github.com/Deepanshuyadav5 |

## What I'm looking for

```text
I’m looking to work on real-time AI systems—RAG pipelines, LLM apps, and backend services on GCP—where I can ship production deployments, control latency/cost, and iterate on model + data workflows.
```

## About

```text
I built a production RAG pipeline at Indixpert Technology, deploying Vertex AI embeddings with pgvector on Cloud Run and serving real-time AI responses through 15+ async REST endpoints.

To keep costs and latency down, I added a semantic caching layer to reduce redundant Gemini API requests and replaced Vertex AI Vector Search with pgvector on Cloud SQL.

I also implemented an auto-escalation pipeline where sentiment scoring triggers P1 ticket creation and agent handoff, designed for zero human triage.

Outside that work, I’ve shipped AI apps like Langalytics for conversational CSV analysis and a YOLOv8-based traffic management system for detection, tracking, and counting.
```

## Experience

### AI Research Intern

Indixpert Technology. May 2026 - Jul 2026

```text
Designed and deployed a production RAG pipeline using Vertex AI embeddings, pgvector, and Gemini 2.5 Flash on Cloud Run with FastAPI. Implemented semantic caching and auto-escalation pipeline with real-time sentiment scoring.
```

Skills: Vertex-AI, Pgvector, Gemini, fastAPI, Cloud-Run, Cloud-SQL, Pub-Sub, Cloud-Storage, IAM, Docker, Python, PostgreSQL, RAG, Sentiment-Analysis

## Education

### DIT University

Bachelor of Technology, Information Technology. 2023 - Present. Grade: 7.36/10

```text
Pursuing Bachelor of Technology in Information Technology with a CGPA of 7.36/10.
```

## Tech stack

- GitHub
- PostgreSQL
- OpenCV
- Java
- PyTorch
- scikit-learn
- FastAPI
- Gemini
- SQL
- LangChain
- Groq
- pgvector

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

## People also viewed

- [R Ajay Kumar](https://himalayas.app/@rajaykumar): Machine Learning Intern, Likwid AI
- [Aditya kumar Arya](https://himalayas.app/@adityakumararya): GenAI Intern, Ingenious E Brain
- [Siddartha A Y](https://himalayas.app/@siddartha): Summer ML Research Intern, Indian Institute of Science (IISc)
- [Aakarsh Kumar](https://himalayas.app/@aakarshkumar): Artificial Intelligence Intern, Scalezix
- [Umar Imam](https://himalayas.app/@umarimam): AI Engineer Intern, Codestore Technologies
- [Shramita Maheshwari](https://himalayas.app/@shramitamaheshwari): AI Intern, Infosys Springboard
- [Ashish Kumar User](https://himalayas.app/@ash-iiiiish): Machine Learning Intern Team Lead, Remote Intakeoff
- [Jesman User](https://himalayas.app/@jesmanuser): AI/ML Intern, Innovate Intern
- [yagav yagav](https://himalayas.app/@yagavyagav): AI Intern, Integra BPO Pvt Ltd
- [Sai Sasidhar Paluri](https://himalayas.app/@saisasidharpaluri): AI Intern, Tecdatum Infoservices Pvt. Ltd.
