We are experts in:
real-time pipelines
data mining
microservices
distributed systems
databases
machine learning
We build scalable high-loaded systems that:
  • processed 1.5 million user events\sec using Kafka and Spark;
  • calculated metrics by telecom logs on petabyte scale;
  • generated recommendations under load of 15000 rpsђ combining batching and streaming approaches;
  • crawled data in†distributed mode from internet sites;
  • streamed data with back-pressure and auto-scaling according to current workload (s3, ftp, databases, rest, message queues);
  • displayed individual advertisements for drivers on highway banners in real-time.
We are
Alexander Konopko
Backend / Big Data
Alexander Konopko
Oleg Kuznetsov
Distributed Systems / Big Data
Oleg Kuznetsov
Ilya Koshelev
Backend / Search Engines
Ilya Koshelev
Vladislav Grozin
Data Scientist
Vladislav Grozin
We came from
YandexrechrelevancesematextAol.
We use and contribute to the best open source software:
sparkkafkaakka-httpkamon.io