Sr. Computer Vision Engineer

Company: Wraith Int Tech Solutions Pvt. Ltd.

Location: Hyderabad, India

Experience: 6-8 years

Company Overview:

Wraith Int Tech Solutions Pvt. Ltd. is a pioneering AI-based company specialising in cutting-edge computer vision and robotics solutions. Our expertise spans human perception, robotic automation, and AI-driven optical systems. We develop advanced technology that enhances efficiency, accuracy, and automation in Defence and commercial applications.

Position Overview:

We are seeking a Mid-Level Computer Vision Engineer to contribute to the development of advanced AI-driven computer vision applications. The ideal candidate will work on image processing, deep learning models, real-time video analytics, and sensor fusion to create innovative solutions for robotics, automation, and Defence applications.

Key Responsibilities:

Computer Vision & AI Development

Develop and optimize computer vision algorithms for object detection, tracking, segmentation, and recognition.
Implement deep learning models for image classification, scene understanding, and pattern recognition.
Work with OpenCV, TensorFlow, PyTorch, and other AI frameworks to develop vision-based applications.
Optimize inference pipelines for real-time processing on edge devices and embeded systems.
Perform image enhancement, denoising, feature extraction, and 3D reconstruction.

Sensor Integration & Data Processing

Process data from RGB, thermal, LiDAR, depth cameras, and multispectral sensors.
Develop sensor fusion techniques to improve perception accuracy and robustness.
Implement calibration and stereo vision techniques for robotics and automation applications.
Optimize data pipelines for low-latency real-time vision processing.

Software Development & Optimization

Develop and maintain efficient, production-ready code in Python and C++.
Optimize deep learning and computer vision pipelines for edge computing and embedded platforms (NVIDIA Jetson, ARM, FPGA, etc.).
Deploy AI models on cloud and on-premise computing architectures.
Utilize CUDA, TensorRT, and OpenCL for GPU acceleration.

Testing & Validation

Conduct performance benchmarking and fine-tuning of AI models for real-world scenarios.
Develop automated testing frameworks for model validation.
Perform error analysis, hyperparameter tuning, and model retraining to improve accuracy.

Cross-Functional Collaboration

Work closely with robotics, embedded systems, and software engineering teams.
Collaborate with product teams to align computer vision solutions with customer requirements.
Contribute to technical documentation, research reports, and patents.

Innovation & Continuous Learning

Stay updated with state-of-the-art AI research and emerging computer vision trends.
Implement new machine learning architectures and research papers into production.
Participate in internal R&D initiatives to enhance vision-based solutions.

Required Qualifications:

Bachelor's or Master’s degree in Computer Science, Electrical Engineering, AI/ML, or a related field.
6-8 years of experience in computer vision, AI, or deep learning.
Proficiency in Python, C++, OpenCV, TensorFlow, PyTorch.
Strong understanding of image processing techniques and deep learning architectures.
Experience working with camera sensors, LiDAR, and embedded vision systems.
Knowledge of edge computing and real-time video analytics.
Experience with Linux, Docker, and cloud-based AI deployments.
Experience of leading a project.

Preferred Qualifications:

Experience with Defence, robotics, or autonomous systems applications.
Knowledge of SLAM (Simultaneous Localization and Mapping) and 3D vision.
Familiarity with CUDA, TensorRT, ONNX, or FPGA-based acceleration.
Strong mathematical foundation in linear algebra, signal processing, and probabilistic models.
Contributions to open-source computer vision projects or research publications.