# Pankaj Yadav

Pankaj Yadav is a remote worker on Himalayas, Machine Learning Engineer at KlearNow.AI, based in India.

Source: https://himalayas.app/@pankajyadav8523

```text
Hi, I'm Pankaj Yadav, a Machine Learning Engineer with 1.8+ years of experience in AI/ML, specializing in LLMs, Document AI, and Agentic AI systems.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | India |
| Authorized to work in | India |
| Salary expectations | 30k+ USD |
| Job categories | Machine Learning Engineer, Software Engineer |
| Skills | Large Language Models, LLM Fine tuning, Multi agent orchestration, AI Agents, Vector Search, Documentation Extraction, Machine Learning, LLM, DocumentAI, RAG, Agentic AI, Fine Tuning, LoRAs, QLoRA, Prompt Engineering, prompt optimization, Quantization, Embeddings, Semantic Search, Natural Language Processing, Computer Vision |
| LinkedIn | https://linkedin.com/in/pankaj-yadav-563101250 |
| GitHub | https://github.com/pankajyadav8523 |

## About

```text
At KlearNow.AI, I architected and deployed an AGNO-based multi-agent Document AI system using Claude 4.5 Sonnet. It orchestrates six microservices for document classification, OCR, and structured data extraction, processing 3,000+ documents per day with 99% reliability.

I modernized document extraction by moving from LayoutLM and BERT to an LLM-powered architecture that adapts to 1,000+ document templates without template-specific retraining. I also developed a Validation Agent that enforces schema rules, reducing downstream errors and manual correction effort.

As a Machine Learning Engineer Intern at KlearNow.AI, I fine-tuned Qwen and LLaMA with LoRA/QLoRA and optimized prompting strategies. At Beans.ai, I developed a CNN-based application to detect parking, roads, and building entrances, and created indoor maps using ArcGIS.

My projects include email intent classification and routing, multimodal document classification with vector retrieval, and document information extraction. I’ve worked across applied machine learning, LLMs, computer vision, and production ML systems.
```

## Experience

### Machine Learning Engineer (current)

KlearNow.AI. Jun 2025 - Present

```text
Architected and deployed an AGNO-based multi-agent Document AI system using Claude 4.5 Sonnet, orchestrating 6 microservices for document classification, OCR, and structured data extraction. Modernized document extraction workflows by migrating from LayoutLM and BERT to an LLM-powered architecture, and engineered a Validation Agent enforcing 14+ schema rules on LLM outputs.
```

Skills: Claude-Sonnet-4.5, RAG, Python, Agno, Claude-4.5-Sonnet, DocumentAI, Microservices, OCR, LLM, Kafka, gRPC, AWS-SQS, Event-Driven-Architecture

### Machine Learning Engineer Intern

KlearNow.AI. Mar 2025 - May 2025

```text
Fine-tuned Qwen and LLaMA using LoRA/QLoRA on 4-bit quantized models, reducing GPU memory usage by 60% and improving field-level accuracy by 18%. Optimized one-shot and few-shot prompting strategies and developed image preprocessing pipelines for OCR optimization.
```

Skills: Python, Qwen, LLaMA, LoRAs, QLoRA, Quantization, Prompt-Engineering, OCR, Image-Preprocessing

### Software Engineering Intern

Beans.ai. Jun 2023 - Aug 2023

```text
Created indoor maps for 10+ facilities using ArcGIS and geospatial datasets, improving delivery routing accuracy. Developed a CNN-based detection application for parking, roads, and building entrances with Grad-CAM visualization, achieving 96% accuracy across 100K+ images.
```

Skills: Python, ArcGIS, Geospatial, CNN, Grad-CAM, Computer-Vision

## Education

### Sitare University

B.Tech, Computer Science Engineering. 2022 - Present

```text
Pursuing a Bachelor of Technology in Computer Science Engineering at Sitare University, Lucknow, with an expected graduation in 2026.
```

## Tech stack

- Kubernetes
- Python
- Java
- C
- PyTorch
- scikit-learn
- Flask
- Transformers
- gRPC
- Docker
- SQL
- XGBoost
- Qdrant
- Qwen
- Agno
- Retrieval-Augmented Generation (RAG)
- Apache Kafka
- AWS

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

## People also viewed

- [Ayush Patel](https://himalayas.app/@ayushpatel_ai): Senior LLM Engineer, Infocusp Innovations
- [Shagun Paul](https://himalayas.app/@shagunpaul): AI/ML Engineer, XansrMedia
- [YASH SHUKLA](https://himalayas.app/@yashshukla2): AI Intern Keplor.ai, Keplor.ai
- [TEERTH CHAUHAN](https://himalayas.app/@teerthchauhan): AI Agentic Developer Intern, Toothlens
- [Bhargav Reddy](https://himalayas.app/@bhargavreddy2): Machine Learning Intern, Intrust Innovation Labs
- [poojitha paladugu](https://himalayas.app/@poojithapaladugu): AI/ML Engineer, Alphastream
- [Gayatri Talathi](https://himalayas.app/@gayatritalathi): AI Engineer, Nurix AI
- [Nabil Khalfe](https://himalayas.app/@nabilkhalfe): AI/ML Research Intern, Aortem.io
- [Saumya Gupta](https://himalayas.app/@saumyagupta5): AI Engineer, Cognizant Technology Solutions
- [Geet Sharma](https://himalayas.app/@geetsharma): Senior Software Engineer AI, Amzur Infotech Pvt. Ltd.