Senior Computer Vision Engineer (Targeting)

The Role:

We are looking for an experienced Computer Vision Engineer to develop and optimize object detection, object classification and lock-on-target algorithms for UAVs. You will be responsible for developing computer vision models to enhance UAV autonomy in challenging environments.

Must have skills:
● 3+ years of commercial experience in Computer Vision and Machine Learning preferably in UAVs, robotics, or autonomous systems
● Proficiency in Python
● Experience with TensorFlow and OpenCV
● Experience with object detection, object classification and tracking algorithms
● Experience with different footage formats: RGB, greyscale, infrared
● Experience in deploying and optimizing models for single-board computers such as Raspberry Pi or low-budget hardware like FPGA
● Familiarity with UAVs, their typical on-board real-time CV pipelines
● Understanding of key performance-defining metrics of computer vision algorithms
● Experience with deep learning, neural networks and CNN
● Intermediate level of English

Nice to have skills:

● Familiarity with YOLO and PyTorch
● Familiarity with drone flight control principles
● Familiarity with Linux
● Familiarity with C++ or Rust
● Familiarity with MAVLink and MSP protocols
● Familiarity with ArduPilot and BetaFlight autopilots

● Experience with Google Coral AI accelerator or other edge TPUs
● Familiarity with AirSim, Unreal Engine, Gazebo or other simulation software

Your responsibilities:

● Develop, train, and optimize computer vision models for real-time object detection, classification and locking on static and dynamic targets for different types of UAVs
● Collaborate with UAV and embedded engineers for deploying CV models to hardware as a part of solution enhancing UAV autonomy
● Develop model performance metrics for evaluating model accuracy and inference
● Perform flight simulation, participate in field testing and flight data analysis to validate model performance
● Optimize the models for various weather conditions, low lighting and other environmental challenges as well as low-budget hardware