Computer Vision Engineer

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 computer vision and GIS, and if that interests you, read on.

We are looking for an experienced Computer Vision Engineer to own the design, development, and deployment of advanced CV algorithms – with a particular focus on GIS applications, image synthesis, and real-time perception pipelines. This is a hands-on engineering role in a startup where theoretical knowledge without execution has no value. You will work across the full pipeline: from data collection and preprocessing through model development and production deployment.

Requirements

• Bachelor's or Master's degree in Computer Science, Computer Engineering, Applied Mathematics, Physics, or a related technical field

• 2+ years of hands-on experience in computer vision or 3D reconstruction

• Strong understanding of multi-view geometry, camera models, and epipolar constraints

• Practical experience with photogrammetry pipelines (OpenSFM, COLMAP, OpenMVS, or similar)

• Working knowledge of 3D Gaussian Splatting or Neural Radiance Fields (NeRF) — you've trained models, not just read the papers

• Proficient in Python and C++; comfortable with PyTorch

• Experience with CUDA or GPU-accelerated computing

• Familiarity with point cloud and mesh processing (Open3D, PCL, or similar)

• Ability to read, reimplement, and adapt methods from recent research papers

Responsibilities

• Designing and implementing 3D Gaussian Splatting pipelines — from point cloud initialization through training to real-time rendering

• Improving and maintaining our existing photogrammetry and orthophoto generation workflows (Structure-from-Motion, Multi-View Stereo, mesh reconstruction)

• Optimizing reconstruction quality and performance: memory footprint, training speed, rendering FPS

• Developing tooling for data preprocessing — camera calibration, pose estimation, image undistortion

• Benchmarking reconstruction quality (PSNR, SSIM, LPIPS) and building automated evaluation pipelines

• Collaborating with the product team to ship Gaussian Splatting as a user-facing feature

• Staying current with the fast-moving radiance field literature and prototyping promising ideas

Would be a plus

Security Eligibility Our platform is actively used by the Armed Forces in live operations. As an Estonian-Ukrainian defense 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.

• Experience with real-time rendering (OpenGL, Vulkan, WebGPU)

• Contributions to open-source 3DGS / NeRF projects

• Background in drone or aerial photogrammetry workflows

• Familiarity with geo-referenced coordinate systems, orthomosaic stitching, and GIS tooling

• Experience deploying CV models to production (model serving, containerization, CI/CD)

• Published research or conference papers in computer vision or graphics