Who we are
DoubleVerify is a big data and analytics company. We track and analyze tens of billions of ads every day for the biggest brands in the world like Apple, Nike, AT&T, Disney, Vodafone, and most of the Fortune 500 companies. If you ever saw an Ad online via Web, Mobile, or CTV device then there are big chances that it was analyzed and tracked by us.
We operate at a massive scale, our backend handles over 100B+ events per day, we analyze and process those events in real-time while making decisions on the environment where the ad is running and all the user interactions during the Ad display lifecycle. We verify that all Ads are Fraud Free, Brand Safe, in the right Geo and highly likely to be viewed and engaged, all that in less than a fraction of a second.
We are global, we have R&D centers in Tel Aviv, New York, Finland, Belgium, Berlin, and San Diego. We work in a fast-paced environment and have a lot of challenges to solve. If you like to solve big data challenges and want to help us build a better industry then your place is with us.
What will you do
You will build a variety of models to analyze millions of textual data points every day across the web, Smart TVs, YouTube, Facebook, Twitter, Instagram, TikTok and more to detect the content categories they are about.
You will work with huge scales, in a cutting edge environment with a superb team, building advanced ensembles of models.
Your work will help advertisers avoid negative or irrelevant content, and target the type of content that is most relevant to their brand, by doing that you help them feel comfortable to invest their money in online free platforms and keep the web free for all.
Who you are
- BSc. in Computer Engineering/Electrical Engineering/Physics /Computer Science/Computational Linguist or, a related technical field from a leading institution or equivalent experience.
- Strong background, 5+ years of experience required in classical NLP, Machine Learning, and Deep Learning algorithms.
- Previous experience in text classification, token / character-level, context-attention and runtime optimization.
- Hands-on experience with toolkits for Deep Learning such as TensorFlow/PyTorch.
- Hands-on experience with toolkits for NLP such as re/difflib/NLTK/Spacy,/Gensim.
- Hands-on experience with building novel deep learning architectures that made it to production.
- A team player with good communication skills.
- Highly motivated with a passion for technological innovation.
- Extensive background in Computational Linguistics
- Experience with time series processing
- Experience with modern NLP methods (transformers, 1D.CNNs for NLP, topical HDBSCAN, etc)