Analyst-Developer for Maps

Analyst-Developer for Maps

Yandex Maps' Geosearch helps millions of people worldwide find the places they need every day. We handle a wide variety of queries: from the simple "тамақтану" in Kazakh to the complex "Boğaz manzaralı hoş bir restoran" in Turkish.

Our main task is to understand the user's intent in a fraction of a second, no matter what language they write their query in or where in the world they are, and show on the map exactly what they are looking for. We turn a text query into a geographical answer, taking into account a huge number of factors: from traffic and opening hours to cultural specifics and implicit preferences.

Maps are a core technology for many of Yandex's urban services, such as Yandex Taxi, Delivery, and Yandex Food.

Why this is an interesting and challenging task

• Working in international geosearch is a unique challenge at the intersection of technology, language, and culture. Unlike classical web search, we deal with the physical world, and that changes everything.
• Language barrier. A user may search in Russian in Turkey, in English in Armenia, or use transliteration. We need to understand queries in different languages, mixed queries (when a single query contains several languages), and handle the variety of names for the same place (Eiffel Tower, Эйфелева башня, tour Eiffel).
• Cultural and local specifics. The concept of "city center," "popular place," or "best coffee" in Istanbul, Yerevan, or Dubai are three different things. Our models must adapt to the local context and understand what is important for a user in a specific country.
• Multifaceted user needs. The same query "Apple" can mean a tech store, a company office, or a fruit market. Our algorithms must determine the correct context in real-time, based on geolocation, time, and user history.
• Scale and speed. All this complex understanding must work with minimal latency for millions of users simultaneously. This requires not only smart but also incredibly efficient models.

You will be working on a product where the result of your code instantly impacts the experience of millions of people, helping them navigate unfamiliar cities and discover the world.

What tasks await you

A/B Testing and Model Deployment You will need to develop pipelines for rapid hypothesis testing and roll into production only those solutions that have proven their effectiveness on real users.

Working with Geodata You will generate new features based on geodata and user behavior.

Generative Approaches We are exploring how generative models can help in understanding complex, detailed queries ("looking for an inexpensive cafe where I can bring a dog and that has power outlets for a laptop") and even in forming personalized recommendation responses for the user.

LLM for Zero-Shot and Few-Shot Tasks When we have little data for training, we use LLMs to quickly solve tasks such as query classification, attribute extraction, and even generating synthetic data for training other models, which significantly accelerates launch in new markets.

More about analytics at Yandex — in the channel Yandex for Analytics

What we expect from you

• Proficiency in Python
• Strong knowledge of probability theory and mathematical statistics
• Ability to build metrics and test hypotheses
• Ability to formulate hypotheses, conduct A/B experiments, and interpret results