Staff Machine Learning Engineer (Ads Conversion Modeling)
Мэтч & Сопровод
Покажет вашу совместимость и напишет письмо
Описание вакансии
TL;DR
Staff Machine Learning Engineer (Ads Conversion Modeling): Responsible for developing and executing a vision for the evolution of the machine learning technology stack for the conversion modeling team, building ML models to improve user ads action prediction. Focus on user sequence modeling, embedding features, model quantization, utility alignment, and RoAS optimization.
Location: Must be based in the US, but can be situated anywhere in the country. This role will need to be in the office for in-person collaboration 1-2 times/month.
Salary: $176,924—$364,254 USD
Company
is an equal opportunity employer and makes employment decisions on the basis of merit.
What you will do
- Lead the tech direction and responsible for the development of state-of-the-art applied machine learning projects for the ads conversion modeling team
- Coach and mentor engineers for the conversion modeling team
- Design features and build large-scale machine learning models to improve user ads action prediction with low latency
- Develop new techniques for inferring user interests from online activity
- Mine text, visual, user signals to better understand user intention
- Work with product and sales teams to design and implement new ad products
Requirements
- MS or PhD degree in Computer Science, Statistics or related field
- 6+ years of industry experience building production machine learning systems at scale, data mining, search, recommendations, and/or natural language processing
- 2+ years of experience leading projects/teams
- Strong mathematical skills with knowledge of statistical methods
- Cross-functional collaborator and strong communicator
Nice to have
- Background in computational advertising is preferred, but not required
Culture & Benefits
- The workplace should be equitable, inclusive, and inspiring for every employee.
Будьте осторожны: если вас просят войти в iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →