Machine Learning Scientist II

Dear Candidate,

Before submitting your resume, please pay attention to the location – we will not be able to review your resume and provide feedback if you are not (in fact) located in the location of the vacancy.

Thanks for understanding

About the project – №1 Travel platform in the world!

We believe that we are better together, and at company we welcome you for who you are. Our workplace is for everyone, as is our people powered platform.
At company, we want you to bring your unique identities, abilities, and experiences, so we can collectively revolutionize travel and together find the good out there.

About the position:

Are you ready to revolutionize the way travelers discover and explore the world? Join Machine Learning Team as a Machine Learning Scientist II, and embark on a thrilling journey to build the next generation Points of Interest (POI) system.

The entire project platform is built on top of our POI metadata for the millions of hotels, attractions, and restaurants listings. This role is pivotal in maintaining the accuracy, coverage, and high-quality place listings that form the bedrock of Clients’ unrivaled user experience. As a ML Scientist II, you will partner with product and engineering to create innovative solutions that evaluate, match and integrate POI data from different sources to build the most accurate, complete, fresh & rich database of travel-related POIs in the world.

What you’ll do:

Work with product and engineering to understand the business problems related to place metadata, including how it’s processed and stored, and define the requirements for machine learning models and algorithms to solve them.
Automate ETL pipelines to process large databases of POIs from different sources efficiently and reliably.
Prototype, deploy, and maintain new models and algorithms for POI matching/conflation, source evaluation, identifying closed businesses, scraping metadata, extracting attributes from UGC, and flagging inaccurate data
Communicate progress, experimental findings, and insights clearly and concisely to both technical and business stakeholders

What we are looking for:

A master’s degree or PhD in computer science, data science, engineering, statistics, or a related field.
2+ years of experience in developing and deploying end-to-end machine learning models and algorithms at scale.
Proficiency in Python, R or a similar numerical/statistical programming language
Ability to interpret and write complex SQL queries
Experience with handling data heterogeneity, incompleteness, duplication, and uncertainty issues in large datasets
Preferred: Experience working with large POI databases and/or geospatial data
Preferred: Experience with LLMs and traditional NLP techniques
Preferred: Experience with text embeddings generation and manipulation, as well as storage and retrieval technology such as vector databases

Why join us:

Ability to work remotely from anywhere in the world
Close cooperation with the development team and client
Opportunity to influence product development
Professional growth: the certification preparation course is free for our specialists. The company pays for two attempts to pass the exam, regardless of the exam result
We cover English classes (with a native speaker)
Boost professional brand: you can participate in local conferences as a listener or as a speaker
Regular team buildings: have fun with teammates
Gifts for significant life events (marriage, childbirth)
Tech and non-tech Zazmic Communities: support and share experience with each other