# Makireddy Vighnesh

Makireddy Vighnesh is a remote worker on Himalayas, Machine Learning Engineer at Aiverbalyze Technologies Private Limited, based in India.

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

```text
Machine Learning Engineer at Aiverbalyze Technologies, improving multilingual Indic ASR across 12 languages and voice-to-voice interactions.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | India |
| Authorized to work in | India |
| Salary expectations | 563k+ INR |
| Job categories | Machine Learning Engineer, AI Engineer |
| Skills | Machine Learning, automatic speech recognition, Multilingual ASR, Speech to Text, Voice to Voice Pipelines, Large Language Models, RAG, Text To SQL, Computer Vision, Image Segmentation, Object Detection, Pose Estimation, Model Fine Tuning, QLoRA, LoRAs |

## About

```text
At Aiverbalyze Technologies Private Limited, I trained and fine-tuned a multilingual Indic ASR system across 12 languages, achieving an average OIWER of 19.2%. I also curated synthetic multilingual datasets and used masked language-token conditioning to improve Malayalam ASR performance by approximately 40%.

I enhanced the existing speech-to-text inference pipeline with on-the-fly audio preprocessing, DeepFilterNet, Silero VAD v6, and utterance segmentation. I also improved the voice-to-voice pipeline with barge-in and interruption handling.

At BigThinx, I built a fashion computer vision pipeline for foreground segmentation and pose estimation from two-view images. I enhanced low-resolution and low-light inputs, improving existing pipeline performance by 30%, and deployed the system on a VM with a Gradio interface.

At IF MedTech, I fine-tuned and quantized a Vision Transformer for medical imaging, reaching 89% accuracy. I also built medical image workflows and implemented a medical RAG application; in my projects, I fine-tuned Qwen3-4B for text-to-SQL and developed a document-querying RAG system.
```

## Experience

### Machine Learning Engineer (current)

Aiverbalyze Technologies Private Limited. May 2026 - Present

```text
Trained and fine-tuned a multilingual Indic ASR system based on Nemotron ASR 3.5 / FastConformer RNN-T across 12 Indic languages, achieving an average OIWER of 19.2%. Enhanced STT inference pipeline with audio preprocessing, DeepFilterNet, Silero VAD v6, and utterance segmentation, and improved voice-to-voice pipeline with barge-in and interruption handling.
```

Skills: ASR, FastConformer, RNN-T, DeepFilterNet, SileroVAD, WER, Synthetic-Data-Generation, Multilingual-NLP, Python, PyTorch

### Computer Vision Intern

BigThinx. Aug 2025 - Feb 2026

```text
Built a fashion-domain computer vision pipeline combining U-Net, P3M-Net, DWPose, and MediaPipe for foreground segmentation and pose estimation on 2-view image inputs. Enhanced low-resolution and low-light inputs using LLFormer and KANT, improving pipeline performance by 30%, and deployed the system on a VM with a Gradio interface.
```

Skills: Computer-Vision, U-Net, P3M-Net, DWPose, Mediapipe, SMPL, LLFormer, KANT, Gradio, Python

### AI/ML Intern

IF MedTech. Jan 2025 - May 2025

```text
Fine-tuned a Vision Transformer (ViT) on a limited medical imaging dataset and quantized it to INT8, achieving 89% accuracy with reduced model size and inference time. Built medical image workflows using Faster R-CNN for anatomical region detection and DeepLabV3 for semantic segmentation, and implemented a medical RAG application using vector embeddings and Llama3-8B.
```

Skills: Vision-Transformer, INT8-Quantization, Faster-RCNN, DeepLabv3, RAG, Llama3, PyTorch, Medical-Imaging

## Education

### Indian Institute of Information Technology, Manipur

Bachelor of Technology, Computer Science and Engineering. 2021 - 2025

```text
Pursued a Bachelor of Technology in Computer Science and Engineering from 2021 to 2025.
```

### DeepLearning.AI

Generative AI with Large Language Models, Artificial Intelligence. 2024 - 2024

```text
Completed the Generative AI with Large Language Models certification in 2024.
```

### DeepLearning.AI

Neural Networks and Deep Learning, Deep Learning. 2024 - 2024

```text
Completed the Neural Networks and Deep Learning certification in 2024.
```

## Tech stack

- GitHub
- Docker Compose
- MySQL
- MongoDB
- Node.js
- EasyOCR
- React
- JavaScript
- Python
- C++
- C
- PyTorch
- Gradio
- Flask
- FastAPI
- Transformers
- TypeScript
- Git
- Docker
- LangChain
- LlamaIndex
- Ollama
- OpenRouter
- DeepSeek
- Unsloth
- MediaPipe

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

## People also viewed

- [Abhinav Painuli](https://himalayas.app/@abhinavpainuli): Machine Learning Intern, IIT Bombay (BharatGen)
- [Anamika User](https://himalayas.app/@anamikauser2): AI Intern, CD
- [Pranjal Raghava](https://himalayas.app/@pranjalraghava): Data Scientist, ValueMatrix AI
- [Kaushik User](https://himalayas.app/@kaushikuser3): Software Engineer (AI/ML), Worktual
- [Prema Gudadinni](https://himalayas.app/@premagudadinni): AI/ML Intern, Vocab.ai
- [Priyangshu Karmakar](https://himalayas.app/@priyangshukarmakar): Remote AI Trainer, Scale AI
- [Govind Kumar](https://himalayas.app/@govindkumar3): AI/ML Engineer, NIT Calicut
- [vaishali manorama manda](https://himalayas.app/@vaishalimanoramamand): Associate Analyst, PurpleTalk India Pvt. Ltd.
- [Srujana G](https://himalayas.app/@srujanag): Associate AI Engineer, Zynthora.ai
- [Dnyaneshwari Pawale](https://himalayas.app/@dnyaneshwaripawale): AI Engineer, AI India Innovations
