Computer Vision Engineer
About us
Farsight Vision converts flight footage into digital 2D and 3D twins for real-time intelligence in GNSS-denied environment, making analytics and situational awareness convenient and accessible while saving time and effort. We create multi-layered digital twins of terrain with dynamic tracking and object/landscape monitoring and predicting.
We are looking for an experienced Computer Vision Engineer to design and implement advanced computer vision algorithms, particularly within the GIS domain. You will work on practical, production-ready solutions for our platform, including image analysis, synthesis, and manipulation. The role involves identifying technical challenges, contributing to research initiatives, and delivering reliable CV modules that can be integrated into real systems. You should be able to combine solid theoretical knowledge with hands-on problem-solving and independent execution.
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
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
Nice to have
- 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
Application Process
- Submit your CV and a brief cover letter explaining your interest and experience.
- Complete a test assignment to demonstrate your skills and approach to solving real-world problems.
- Interview with our technical team and leadership.
Why us
- Impactful projects. Your work will strengthen the country’s defense capability and support the Ukrainian Armed Forces; your results will directly help our defenders;
- Professional team and startup dynamics. You will become part of a team of professionals who develop cutting‑edge technologies and value teamwork. Our culture encourages knowledge exchange, innovation and rapid growth.
- Flexible conditions. Remote work, flexible schedule, paid vacation and sick leave.