Deep Learning Engineer

Role Overview
We are looking for a Deep Learning Engineer with experience in computer vision, object detection, tracking, and segmentation. The candidate should have strong programming skills in Python and C++, along with knowledge of robotics, point cloud processing, and mathematical concepts used in computer vision.

Key Responsibilities

Develop and implement deep learning models for object detection and segmentation.
Implement 2D and 3D object tracking algorithms.
Work with image and point cloud data for perception tasks.
Collect, process, annotate, and augment datasets for model training.
Use OpenCV and PCL for image processing and point cloud operations.
Develop and integrate perception algorithms using ROS.
Optimize algorithms for real-time performance on Linux systems.
Evaluate model performance and improve accuracy and robustness.

Required Skills

Programming: Python and C++.
Deep Learning: Object detection, segmentation, model training, and evaluation.
Computer Vision: OpenCV, image processing, and feature extraction.
3D Perception: Point cloud processing using PCL.
Object Tracking: 2D and 3D object tracking algorithms.
Robotics: ROS fundamentals and sensor data processing.
Data Preparation: Data collection, annotation, preprocessing, and augmentation.
Mathematics: Linear algebra, geometry, coordinate transformations, probability, and basic statistics.
Operating System: Linux and basic debugging tools.

Preferred Qualifications

Experience deploying deep learning models for real-time applications.
Knowledge of Kalman filters and data association algorithms.
Familiarity with GPU-based inference and model optimization.