# Prakhar Keshari

Prakhar Keshari is a remote worker on Himalayas, Machine Learning Engineer at Zoop.One, based in India.

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

```text
Machine Learning Engineer at Zoop.One who cut GPU serving costs by over 90% for production face liveness.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | India |
| Authorized to work in | India |
| Salary expectations | 2208k+ INR |
| Job categories | MLOps Engineer, Machine Learning Engineer, AI Engineer |
| Skills | Machine Learning, Computer Vision, MLOps, DocumentAI, OCR, Natural Language Processing, Large Language Models, Vision Language Models, Model Serving, Model Quantization, Knowledge Distillation, GPU Inference, Model Optimization, PyTorch, Python |
| LinkedIn | https://linkedin.com/in/prakhar-keshari |
| GitHub | https://github.com/Prazhar |

## About

```text
At Zoop.One, I owned training, inference, deployment, monitoring, and rollout for a production face-liveness system serving 5K–6K requests a day. I replaced a third-party liveness API with in-house GPU inference, reducing annualized serving cost by over 90%.

I also built motor-claims document classification and OCR workflows, with a field-level accuracy framework that scored 759 documents at 96% exact-match accuracy. By improving claims intake and implementing semantic document retrieval, I helped cut manual review time by 35%.

At Qualcomm, I integrated torch.compile into neural network quantization libraries, achieving a 20% runtime speedup and 15% GPU memory reduction. My project work includes a knowledge-distillation pipeline for 500K+ noisy production strings and deep-learning research on channel estimation.
```

## Experience

### Machine Learning Engineer (current)

Zoop.One. Jan 2025 - Present

```text
Owned end-to-end model serving for production ML systems including face liveness, claims document AI, and vehicle damage inspection. Reduced serving costs by over 90% and improved accuracy and efficiency across multiple AI initiatives.
```

Skills: Python, PyTorch, fastAPI, Docker, Kubernetes, GCP, Jenkins, CI-CD, GPU-Inference, YOLO, OCR, DocumentAI, NLP, LLM, VLMs, Embeddings, Vector-Stores, OpenCV

### Interim Engineering Intern

[Qualcomm](https://himalayas.app/companies/qualcomm). Mar 2024 - Sep 2024

```text
Integrated torch.compile into neural network quantization libraries, achieving a 20% runtime speedup and 15% GPU memory reduction. Implemented per-channel activation scaling for CNNs, recovering 10-12% accuracy lost during quantization.
```

Skills: PyTorch, Model-Quantization, Torch.Compile, CNN, GPU-Optimization, Research

## Education

### Indian Institute of Technology Indore

M.Tech, Communication and Signal Processing. 2022 - 2024. Grade: 8.74/10

```text
Pursued M.Tech in Communication and Signal Processing, achieving a CGPA of 8.74/10.
```

### Jabalpur Engineering College

B.Tech, Electronics and Communication. 2018 - 2022. Grade: 8.18/10

```text
Completed B.Tech in Electronics and Communication with a CGPA of 8.18/10.
```

## Tech stack

- GitHub
- Kubernetes
- K9s
- Jenkins
- OpenCV
- Python
- MATLAB
- TensorFlow
- PyTorch
- scikit-learn
- Keras
- FastAPI
- Linux
- macOS
- pytest
- Git
- Docker
- SQL
- Hugging Face
- OpenAI API
- Bash
- OpenRouter
- Sentence Transformers

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

## People also viewed

- [Shubham Chambhare](https://himalayas.app/@shubhamchambhare): Machine Learning Engineer, Zoop.One
- [Rupinderpal Singh](https://himalayas.app/@rupinderpalsingh): Jr. Software Engineer Intern, Netsmartz
- [Varada Vaidya](https://himalayas.app/@varadavaidya): Machine Learning Engineer, Independent Projects
- [yash jangid](https://himalayas.app/@yashjangid): Machine Learning Engineer, Alignerr
- [SATHWIK User](https://himalayas.app/@sathwikuser): AI Training Data Specialist, NVIDIA via Randstad
- [abhinav sharma](https://himalayas.app/@abhinavsharma6): ML Researcher, Personal Projects
- [Shashvat Aghera](https://himalayas.app/@shashvataghera): AI/ML Intern, JA Assure
- [Shiv Sunder](https://himalayas.app/@shivsunder): Machine Learning Intern, Quantiphi
- [Prince Choudhary](https://himalayas.app/@princechoudhary): AI/ML Engineer, Vinfotech
- [Neal Daftary](https://himalayas.app/@nealdaftary): Student Chairperson, Nirma University ACM Student Chapter
