Computer Vision Intern

Flick2Know; Gurugram District; On-site; INR 167,400 - 279,000; Full time

Job summary

Flick2Know in Gurugram, India seeks a Computer Vision Intern to build and refine an image recognition pipeline. The role starts with dataset management—collection, annotation validation, cleaning, and preprocessing—then moves to model training, augmentation, and evaluation for a production-ready pipeline.

You will work with Python, OpenCV, and annotation tools, contributing to real-world inference quality and documenting data workflows.

Qualifications

• Basic understanding of Computer Vision concepts (Object Detection, Classification).
• Familiarity with Python (OpenCV, Pandas, NumPy).
• Knowledge of image annotation tools (Roboflow, LabelImg, CVAT, etc.).
• Ability to manage and organise large datasets.

Responsibilities

• Organize, clean, and preprocess large-scale retail image datasets.
• Validate and manage annotations (bounding boxes, labels, masks) with Roboflow/CVAT/LabelImg.
• Apply augmentation and prepare datasets for training.
• Train YOLOv5/YOLOv8 models on custom data.
• Evaluate models (Precision, Recall, F1, SKU accuracy).
• Collaborate with product team to improve real-world inference.
• Document the dataset pipeline and share data-quality insights.

Skills

Python

OpenCV

Pandas

NumPy

Image annotation

YOLOv5

YOLOv8

Data preprocessing

Dataset management

Tools

Roboflow

CVAT

LabelImg

Albumentations

Job description

We are looking for a Computer Vision Intern to assist in building and refining our image recognition pipeline. The role will start with dataset management—image collection, annotation validation, dataset cleaning, and preprocessing. Once the foundational data work is complete, you’ll get hands‑on exposure to model training, augmentation, and evaluation, contributing directly to our production‑ready pipeline.

Responsibilities

• Organize, clean, and preprocess large-scale retail image datasets.


• Validate and manage annotations (bounding boxes, class labels, segmentation masks if applicable) using tools like Roboflow or CVAT or LabelImg.


• Apply augmentation techniques and prepare datasets for training.


• Support in training YOLOv5/YOLOv8-based models on custom datasets.


• Run model evaluations (Precision, Recall, F1 Score, SKU-level accuracy).


• Collaborate with the product team to improve real‑world inference quality.


• Document the dataset pipeline and share insights for improving data quality.

Must Have

• Basic understanding of Computer Vision concepts (Object Detection, Classification)


• Familiarity with Python (OpenCV, Pandas, NumPy)


• Knowledge of image annotation tools (Roboflow, LabelImg, CVAT, etc.)


• Ability to manage and organise large datasets

Good To Have

• Experience with YOLOv5 or YOLOv8 (Training, Inference, Fine‑tuning)


• Exposure to image augmentation techniques (Albumentations, etc.)


• Understanding of retail/commercial shelf datasets or product detection problems


• Previous internship or project experience in computer vision is a plus