Machine Learning Researcher (AdTech)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
Machine Learning Researcher (Deep Learning): Designing and implementing deep neural networks to predict internet user behavior within a high-scale AdTech ecosystem with an accent on bidding strategies and recommendation systems. Focus on optimizing model architectures, analyzing A/B tests, and solving data distribution shifts in production environments.
Location: Must be based in Poland (100% remote, hybrid, or onsite in Warsaw or Cracow)
Company
A global AdTech company providing state-of-the-art deep learning-powered marketing technologies for top brands worldwide.
What you will do
- Design and implement deep neural network models to predict Internet users' behavior and preferences.
- Analyze the latest Machine Learning research and implement advanced architectures like Transformers and CNNs.
- Conduct and analyze A/B tests to validate and optimize new modeling solutions.
- Develop new approaches to key issues, such as bidding in first-price auctions.
- Address and solve differences in distribution between training and production data.
- Experiment with transfer learning and new loss functions for product recommendations.
Requirements
- 4+ years of hands-on experience with Machine Learning and Data Science.
- Strong proficiency in programming (Python, Java, Scala).
- Solid knowledge of statistics and probability.
- Practical experience with PyTorch, NumPy, and Pandas.
Nice to have
- Experience in the ML industry.
- Experience in designing recommendation systems.
- Practical knowledge of the company's specific toolset.
Culture & Benefits
- Extremely flexible cooperation conditions with 100% remote options.
- Access to latest technologies and large-scale projects handling billions of advertising views.
- Opportunity to publish research results.
- Collaborative environment with a team of ML enthusiasts.
- Cooperation based on B2B contract or Contract of Mandate.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →