Key Responsibilities
● Design, develop, and implement perception algorithms for various
applications, including object detection, tracking, classification, and scene
understanding.
● Work extensively with video and image processing techniques, including:
● Image Processing: Noise reduction, feature extraction, image
segmentation, image enhancement, color space manipulation,
geometric transformations.
● Video Stabilization: Real-time video stabilization techniques for noisy
or shaky camera inputs.
● Motion Estimation: Developing techniques to estimate the motion of
objects or the camera.
● Develop and integrate perception pipelines using NVIDIA DeepStream and
GStreamer for high-performance, real-time processing.
● Optimize perception algorithms for deployment on edge computing platforms
such as Jetson, considering constraints such as power, memory, and
computational resources.
● Collaborate closely with hardware engineers, and software engineers to
integrate perception solutions into larger systems.
● Stay up-to-date with the latest advancements in computer vision, deep
learning, and robotics perception.
Skills and Requirements
● Bachelor's degree in Computer Science, Electrical Engineering, Robotics, or a
related field.
● Approximately 1-2.5 years of professional experience in Computer Vision
domain.
● Strong proficiency in C++ and Python.
● Hands-on experience with NVIDIA DeepStream SDK for building real time
streaming applications.
● Demonstrable experience with GStreamer for multimedia pipeline
development.
● Extensive experience with image processing techniques (e.g., OpenCV).
● Strong understanding and practical application of video stabilization
algorithms.
● Experience with object detection, tracking, and classification.
● Familiarity with various computer vision algorithms and their applications.
● Experience in solving AI-related problems, particularly in the context of
computer vision and real-time inference.
● Practical experience in optimizing and deploying models on edge computing
devices.
Skills Required
- Bachelor's degree in Computer Science, Electrical Engineering, Robotics, or related field
- Approximately 1-2.5 years of professional experience in Computer Vision
- Strong proficiency in C++
- Strong proficiency in Python
- Hands-on experience with NVIDIA DeepStream SDK
- Experience with GStreamer for multimedia pipeline development
- Extensive experience with image processing techniques (e.g., OpenCV)
- Practical experience with video stabilization algorithms
- Experience with object detection, tracking, and classification
- Experience solving AI-related problems and real-time inference
- Practical experience optimizing and deploying models on edge devices (e.g., Jetson)
What We Do
Paar Autonomy is a deep-tech robotics startup specializing in autonomy solutions and AI-based vision systems for unmanned aerial, ground, and sea vehicles. The company develops multi-sensor, gyro-stabilized gimbal cameras and proprietary agentic AI models designed to provide 'super-human' vision and real-time mission coordination, primarily targeting the global defense market and dual-use industrial applications.
