Aliaksandr S.
Senior Computer Vision Engineer | Video AI | Edge AI | OCR/VLM
I build real-time video/camera AI and OCR/VLM document intelligence systems. Video AI: object detection/tracking, RTSP/WebRTC/GStreamer pipelines, edge inference on Jetson/Intel devices and server GPUs, inspection workflows, and low-latency deployment. Document AI: OCR, VLM/LLM-based parsing, table/form extraction, technical document understanding, structured JSON outputs, and QA-ready pipelines. Over 7 years of production AI engineering across inspection, LiDAR/Scan2BIM, satellite imagery, video analytics, and complex document parsing. I do not just wrap APIs - I build custom inference pipelines that survive real data, latency limits, hardware constraints, and validation requirements.
Earnings and projects
Last 6 months ÷ 6
Last 6 months: $31k
Billed in all: $41,813$42k
$7.8k in the last 6 months
Across 6 contracts
Across 11 contracts
Earnings, last 30 days
Skill rankings: Top 1% in AI Model Training
Ranked by MRR among everyone on Upwork with the skill.
- #4Photogrammetry187 freelancers · 🇪🇸 #1Top 2%🇪🇸#1 of 2
- #6Object Detection & Tracking126 freelancers · 🇪🇸 #1Top 5%🇪🇸#1 of 2
- #11Deep Neural Network301 freelancers · 🇪🇸 #1Top 4%🇪🇸#1 of 7
- #13AI Data Analytics535 freelancers · 🇪🇸 #1Top 2%🇪🇸#1 of 12
- #16AI Model Training1,135 freelancers · 🇪🇸 #1Top 1%🇪🇸#1 of 12
- #30AI Model Development558 freelancers · 🇪🇸 #1Top 5%🇪🇸#1 of 9
- #59Computer Vision2,498 freelancers · 🇪🇸 #1Top 2%🇪🇸#1 of 16
- #121Large Language Model2,726 freelancers · 🇪🇸 #1Top 4%🇪🇸#1 of 14