Computer Vision Engineer [Robotics Perception]

Full-time position

About Farsight Vision

Farsight Vision develops AI-powered geospatial intelligence solutions for defence and security operations. The platform transforms raw aerial and sensor data into real-time 3D environments, actionable analytics, and AI-assisted operational scenarios, enabling enhanced situational awareness, mission planning, and faster decision-making for both human operators and autonomous systems. We operate at the intersection of geospatial data, computer vision, and defence operations - and if that interests you, read on.

We are looking for a Computer Vision Engineer to develop perception for our unmanned ground robot, combining deep learning, classical computer vision, and 3D data processing. You will train and deploy neural networks for scene understanding and object detection, integrate cameras into our perception and localization stack, and develop algorithms that help the robot understand its surroundings.

The role covers the full development cycle: collecting and preparing sensor data, experimenting with models, calibrating and synchronizing sensors, and deploying reliable perception pipelines on a moving robot. You will help define the approach and validate it through hands-on field testing.

Responsibilities:

• Develop, train, and evaluate deep learning models for object detection, semantic segmentation, and scene understanding

• Build datasets, define annotation requirements, and improve data quality and coverage across operating conditions

• Deploy and optimize computer vision models for real-time inference on onboard hardware

• Configure cameras and perform intrinsic and extrinsic calibration between cameras, LiDAR, and IMU

• Integrate camera data into localization pipelines and work with the hardware team on sensor synchronization, including hardware triggering where needed

• Develop point cloud algorithms for obstacle detection and spatial analysis, combining camera and LiDAR data to improve perception

• Define evaluation metrics for accuracy, latency, and robustness, and integrate perception outputs with navigation and control engineers

• Validate and improve the system through field testing on the physical robot in Lviv

Requirements:

• Hands-on experience developing computer vision solutions using deep learning and classical methods

• Practical experience training and evaluating neural networks with PyTorch or a comparable framework, including dataset preparation, augmentation, and error analysis

• Knowledge of camera models, intrinsic and extrinsic calibration, and coordinate transformations

• Strong mathematical foundation in linear algebra, geometry, probability, and numerical methods

• Solid Python and C++ skills, with the ability to turn experimental algorithms into maintainable software

• Experience with 3D data such as point clouds or depth images, and the ability to troubleshoot across sensor data, models, and system integration

• Upper-Intermediate+ English and willingness to participate in hands-on integration and field testing in Lviv

Nice to have:

• Experience deploying and optimizing models on NVIDIA Jetson or other edge AI platforms using ONNX or TensorRT

• Experience with multi-modal learning or camera-LiDAR fusion

• Experience with visual odometry, SLAM, or multi-sensor localization

• Understanding of sensor synchronization, hardware camera triggering, or PTP

• Familiarity with ROS 2 and libraries such as OpenCV, PCL, or Open3D

• Background in outdoor robotics, autonomous navigation, or defence technology

Security Eligibility

Our platform is actively used by the Armed Forces in live operations. As an Estonian-Ukrainian defence technology company handling sensitive operational data, we have a responsibility - legal, ethical, and practical - to ensure the integrity of everyone on our team.

All candidates must be able to confirm the following:

• Neither you nor your close relatives (parents, spouse, siblings, children) reside in Russia, Belarus, or temporarily occupied Ukrainian territories

• You have no regular personal, financial, business, or professional contact with individuals in those territories

• You consent to a deeper security verification if the process advances to later stages

If any of the above criteria are not met, please do not proceed with your application.

Why Farsight Vision

We are a startup operating under real-world conditions - our product is in active deployment, and the pace reflects that. You will work across computer vision research and practical robotics, taking models from initial experiments through deployment and field validation. Your decisions will directly shape how our robot perceives and understands its environment.

We value engineers who take ownership of open-ended problems, test their assumptions, and follow through until their solutions work in the field.

Flexible working hours. Paid vacation and sick leave. Direct access to founders and leadership.

Application Process:

• Apply with your CV and a brief cover letter explaining your interest and relevant experience

• Interview with the Recruiter

• Interview with VP of Engineering

• Complete a short practical assignment involving a control/navigation problem drawn from our platform

• Interview with Lead Robotics Engineer