Senior Computer Vision Engineer
The Role:
We are looking for an experienced Computer Vision Engineer to develop and optimize an autonomous navigation system for UAVs. You will be responsible for developing a solution based on visual-inertial odometry methods in GNSS-denied environments.
Must have skills:
β 5+ years of commercial experience in Computer Vision and Machine Learning preferably in UAVs, robotics, or autonomous systems
β Proficiency in Python
β Experience with OpenVINS
β Experience with such frameworks as TensorFlow and OpenCV, YOLO or PyTorch
β Experience with visual-inertial odometry, camera position estimation, detection and tracking of visual features of static objects
β Understanding of key performance-defining metrics of computer vision algorithms
β Familiarity with AirSim, Gazebo or other simulation software
β Experience with different footage formats: RGB, greyscale, infrared, thermal
β Experience in deploying and optimizing models for single-board computers such as Raspberry Pi, Nvidia Jetson
β Familiarity with UAVs, their typical on-board real-time CV pipelines
β Familiarity with drone flight control principles
β Experience with deep learning, neural networks and CNN
β Intermediate level of English
Nice to have skills:
β Understanding of Kalman filtering and sensor fusion techniques
β Familiarity with Linux
β Familiarity with the MAVLink protocol and ArduPilot
β Experience with Google Coral AI accelerator or other edge TPUs
β Experience with geospatial data processing and GIS tools (e.g., GDAL, Rasterio, QGIS)
Your responsibilities:
β Develop, train, and optimize computer vision models for an autonomous UAV navigation system based on visual-inertial odometry and other methods
β Collaborate with UAV and embedded engineers for deploying CV models to hardware
β Develop model performance metrics for evaluating model accuracy and inference
β Perform flight simulation, participate in field testing and flight data analysis to validate model performance
β Optimize the models for various weather and lighting conditions (including night time) as well as a range of UAV flying speeds/heights with the focus on result reproducibility
β Utilize geospatial data for real-time updating of estimated UAV position