Job Details

Python Developer for Data Mining at Spravochnik, a platform that collects data about organizations. Focus on Python, C++, and ML for parsing, NLP, and Big Data. Hybrid work in Moscow.

Spravochnik is a platform that collects data about organizations. Our system processes millions of signals: user feedback, website updates, corrections from business owners. If you want to work at the intersection of Python, C++, and ML, solving parsing, NLP, and Big Data tasks, join us! Here your skills will turn into technologies that millions of people use every day. What tasks await you: • Optimize the architecture for simultaneous operation of hundreds of parsers, implement an isolated parser execution environment, and increase the efficiency of interaction with PostgreSQL • Create a pipeline for automatic translation of content and data labeling using language models, as well as adapt and configure models (YandexGPT, etc.) for business tasks • Adapt the platform for new countries and languages, organize data processing through YTsaurus MapReduce and an internal AirFlow analog • Develop methods for comparing and normalizing organization attributes and accelerate critical system components in C++

We expect you to: • Have experience with C++ and Python (middle+ level) • Have a deep understanding of algorithms, data structures, and SQL • Be able to write clean, testable code with documentation

What we offer: We value self-development, so we have our own educational platform with 700+ courses. And if you need something special that will really help with work, we can help with payment. This is not all the bonuses — a full list is here: https://yandex.ru/jobs/pages/benefits?utm_campaign=ya_nanimaet