Data Scientist
Our Story:
We’re EX.CO, the world’s leading self-serve video technology platform. We empower publishers to own their video strategy for maximum yield by providing easy-to-use, AI-based solutions for ad serving, monetization, content automation, interactive experiences, and contextual targeting. Our one-stop-shop platform is trusted by some of the largest publishers globally including CBSi, Hearst, MLB, Nasdaq, Refinery29, Sky News, Time, ViacomCBS, VICE, and Ziff Davis. Founded in 2012 with employees located around the world,EX.CO is backed by The Walt Disney Company, Saban Ventures, Viola Group, 83North, and Firstime Ventures.
Your Story:
EX.CO is looking for a Data Scientist to join our R&D team. To become part of our journey in helping digital publishers and businesses improve their business growth, empowering meaningful interactions across their digital assets, generating an undeniable increase in revenue, user engagement, conversions, and overall performance.
Build the next generation of ML algorithms for EX.CO. Focusing primarily on recommendation engines, utilizing NLP and deep-learning techniques for performance optimization.
Lead the architecture’s research, modeling, design, and development to run at scale.
Long story short, you will:
- Design, build, automate, deploy and maintain machine learning production pipelines, utilizing cloud technologies such as cloud AI / Sagemaker
- Deploy and monitor models in production (e.g. building artifacts, measuring model drift, etc.).
- Implement and evaluate recommender engines using NLP and deep-learning techniques, to work in a production environment and run at massive scale.
- Apply complex analytical techniques to derive actionable insights with very good communication skills to write and publish internal documentation to be used by technical and business teams.
- Design and execute technical processes needed for experimentation to support an array of business problems, including experiment ideation, experimental design, monitoring, data analysis, code review and communication of results.
- Keep up with machine learning research and commercial product offerings across a wide variety of machine learning fields including recommendations, NLP, and information retrieval
- Role Key Deliverables: Own current recommendation engine modeling stack and its development processes (creation/specification of tasks, daily updates and commitment to deliverables), research and deploy incremental improvements.
And will be awesome if you have:
- MSc in Computer Science/Statistics/Engineering or related field with a focus on applied statistics, AI, machine learning, or related fields.
- 3+ years applying machine learning to real-world problems in an industrial setting.
- Strong engineering and coding skills, with ability to write high performance production code. Ability to lead, envision and implement improvements of our ML solution and pipelines
- Proficiency in Python, Java, Scala, and/or other equivalent languages.
- Hands-on experience in Machine learning frameworks such as TensorFlow, Scikit-learn, Spark, pytorch, MLib, Pandas, Numpy etc.
- Strong understanding of evaluation methods for recommender systems and ability to run offline and online using experimental design
- Preferred proficiency with data pipelines in Hadoop/Spark in a cloud environment
- Ability to write and execute complex queries in SQL against different database architectures
- Working knowledge of agile development processes and methodologies
- Strong analytical & problem-solving skills, and excellent communication skills