Key Responsibilities

- Design, develop, and deploy computer vision models for object detection, face recognition, OCR, and image classification.

- Build and optimize image and video processing pipelines using OpenCV and Python.

- Train, fine-tune, and evaluate YOLO-based object detection models (YOLOv5/v8 or later).

- Implement OCR solutions using Tesseract, EasyOCR, PaddleOCR, or similar tools for text extraction from images and documents.

- Develop face detection, recognition, and verification systems with a focus on accuracy and speed.

- Build solutions using Vision-Language Models (VLMs) such as CLIP, BLIP, LLaVA, Qwen-VL, and PaliGemma for image captioning, visual question answering, image-text retrieval, and document understanding.

- Fine-tune VLMs for domain-specific use cases using LoRA, QLoRA, and other parameter-productive techniques, and evaluate outputs for accuracy, hallucination, and bias.

Interested candidates can share their updated resume to:

[email protected] (phone hidden)

📌 Computer Vision Engineer (Chennai)
🏢 VeeTechnologies
📍 Chennai