AI Engineer

AI (Computer Vision Engineer) – Job Description

About the Role:
We're looking for a hands-on Computer Vision Engineer to join our fast-paced AI team. You'll own the full lifecycle of CV models — from training to edge deployment — in a high-ownership, move-fast culture.

Key Responsibilities:

• Design, train, and evaluate computer vision models (detection, segmentation, classification)
• Work with YOLO and similar architectures for real-time object detection tasks
• Apply data augmentation strategies and preprocessing pipelines to improve model robustness
• Convert and optimize models for edge deployment
• Deploy and benchmark CV models on edge devices
• Apply quantization, pruning, and distillation to create lightweight, production-ready models
• Collaborate with hardware and software teams to integrate models into end-to-end systems

Responsibilities

• Design, train, and deploy computer vision models, with a focus on YOLO variants, ensuring high accuracy and efficiency.
• Implement data preprocessing and augmentation methods to improve model generalization and robustness.
• Convert trained models into lightweight formats optimized for deployment on edge hardware platforms.
• Develop and refine neural network architectures and machine learning algorithms aligned with project goals.
• Utilize Python, PyTorch, and OpenCV to build and maintain AI pipelines and integrate models into applications.
• Monitor model performance and implement improvements in model training procedures and deployment workflows.
• Research and incorporate advanced techniques in deep learning and computer vision to keep solutions state-of-the-art.
• Collaborate with cross-functional teams to gather requirements and translate them into technical AI implementations.
• Maintain documentation of model development processes, training datasets, and deployment configurations.
• Stay updated on the latest trends in multi-object tracking and MLOps to enhance operational efficiency.
• Own projects from inception to deployment, demonstrating a proactive and ownership-driven approach.
• Troubleshoot and resolve issues arising during model training, evaluation, and deployment phases.