Artem
Shamsuarov
15+ years building production-grade computer vision systems. Specialized in real-time 3D reconstruction, multi-camera pipelines, SLAM, and GPU-accelerated processing. Published researcher with 7+ patents.
Work Experience
- Developed production-ready CV algorithms for multi-camera 3D scanning systems
- Implemented real-time image processing pipelines handling large-scale visual datasets from structured light, laser, lidar, and RGB scanners
- Achieved 10–100× performance improvements through CUDA optimization
- Designed real-time tracking and fusion algorithms, automated defect detection, and quality control systems
- Maintained CI/CD pipelines (Jenkins) and mentored junior engineers
- Built real-time fusion algorithms for mobile 3D scanner with onboard processing
- Implemented 3D reconstruction and SLAM algorithms for production scanning systems
- Achieved 70% latency reduction through CUDA/OpenCL/Vulkan optimization
- Designed next-best-view planning system and software architecture for distributed computing clusters
- Built multi-platform apps (iOS/Swift/ObjC, Windows/C++) for industrial vision
- Developed CV algorithms and apps deployed to millions of mobile users
- Built complete 3D reconstruction pipeline: SfM, SLAM, depth estimation, depth fusion
- Implemented near-duplicate image retrieval and face detection systems
- Published at IEEE CVPR Workshop; secured 3 patents
- Developed optimization algorithms for computational lithography at next-gen semiconductor nodes
- Created C++/Qt/Python tools for Optical Proximity Correction and Resolution Enhancement
- Collaborated with Cadence, Mentor Graphics, Synopsys; published at SPIE; obtained 2 US patents
Technical Skills
Personal Explorations
Side projects spanning computer vision, quantitative finance, and creative tools — built from scratch to explore what interests me.
From-scratch implementation of 3D Gaussian Splatting in C++23/CUDA. Custom differentiable tile-based rasterizer with analytic gradients, fused Adam optimizer as a single CUDA kernel, MCMC densification, and a real-time OpenGL viewer.
Real-time visual odometry on Android. XFeat learned features via ONNX Runtime, Vulkan compute descriptor matching through Kompute, ARM NEON SIMD preprocessing, and 5-point RANSAC pose estimation with keyframe management.
Zero-tap document scanner for Android. Auto-detects document boundaries, captures on stability, corrects perspective with sub-pixel corner refinement. Classical CV pipeline with multi-strategy preprocessing — no ML, no cloud.
Low-latency limit order book and matching engine with lock-free SPSC ring buffers, zero-allocation hot path, slab allocator, and market microstructure analytics (spread, microprice, order flow imbalance, Kyle's Lambda).
GPU-accelerated portfolio optimization with Monte Carlo scenario generation (cuRAND + Cholesky), Mean-CVaR via custom ADMM solver, PCA factor model (15.6x speedup), and rolling-window backtesting with transaction costs.
Desktop guitar practice app — load any Guitar Pro tab (GP3–GP8), plug in via USB, and get real-time pitch detection with hit/miss feedback and scrolling tab playback. A lightweight, free Yousician alternative.
Desktop app for recording vocals over music tracks. Automatic vocal separation via Demucs, cross-correlation alignment of recording to backing track, LUFS normalization (ITU-R BS.1770-4), and one-click export of the final mix.
Publications & Patents
Academic Background
Let's Connect
Open to opportunities in computer vision, real-time systems, and GPU-accelerated computing. Based in Luxembourg, EU citizen.