Process automation

Powerful process automation platform provider was trying to enlarge their development team. They come to peoly with request to provide them managed nearshore development team with experience of integration, RESTfull API and JavaScript as well as knowledge of front-end development. After evaluation period we were able to qualify as an exclusive partner for the project. The assignment is an integration of 3rd party APIs into the customer platform. Within couple of months we expanded dedicated team of 5 to 15 people with specific developer profile which fits with the customer needs. Currently we agreed with customer further extent our team and widen our scope of services and responsibilities.

 

AI video analytics for retail

Customer with long term experience in ML/AI area was looking for highly qualified machine learning developers experienced in real time object detection, tracking and as well as behavioral analysis of the objects in video feeds from retail environment. We created an expert team which consists of ML specialist with experience of real time object detection pipeline (detection model, transfer learning, tracking, behavioral analysis), two senior developers with experience of real time object detection pipeline and Nvidia DeepStream SDK principles, and one annotator with experience of preparing ground truth data for ML models. Our team helped substantially improve current customer solution from the perspective of performance, reliability and speed of processing. 

 

Traffic video analytics for SmartCity

Renowned European system integrator was looking for a software solution for its SmartCity project with special requirements for real time traffic video data analytics. We were able to customize our software modules and to fit all the specific requirements with a short reaction time. We have used our knowledge and software solution to provide specific precise output traffic data for further use in customer SmartCity platform.

 

Web platform visual search

Furniture aggregator platform was looking for extension of their search services by visual search, which allows customers to find similar products just upload the photo taken by customer or downloaded picture. We have prepared the whole service as a separate microservice for customer Kubernetes infrastructure. The team consists of two ML experts and two Senior developers, who completely designed and developed the whole service including communication model with the rest of services. We’ve chosen and prepared the up-to-date architecture (detector, feature vector extractor, approximate nearest neighbor and other services )

Solution1.png