Job Description
The role
You turn raw platform and content data into things the team can act on. You understand data and ML from a developer point of view, and you know how content data from platforms like large video and streaming services is structured, projected and read: views, watch time, engagement, metadata, trends and how they move.
You have worked with real content or consumer data before and used ML techniques to make sense of it, not just built dashboards.
What you will do
Build data pipelines and analysis over content and consumer data: views, watch time, engagement, catalogue and metadata.
Apply ML techniques to spot patterns, segment users, forecast trends and surface what is working.
Model how video and content performance data should be read and projected for product and business decisions.
Work with large datasets from platform APIs and internal sources, and clean the mess before it is usable.
Turn analysis into clear outputs the AI, product and content teams can use.
What we are looking for
Command of our core ML and data stack is mandatory: Python with pandas, NumPy and scikit-learn, strong SQL, and hands-on with at least one of PyTorch or TensorFlow, plus notebooks (Jupyter) for real analysis. XGBoost or LightGBM and a warehouse such as BigQuery are expected too.
One to two years in a data or ML-leaning developer role, ideally with content, media or consumer internet data.
Practical understanding of ML techniques for analysis: regression, classification, clustering, basic forecasting.
You understand how content platform data such as views, watch time and engagement is measured and can be misread.
You can go from a raw dataset to a clear, defensible insight on your own
No Referrers Available
There are currently no referrers available for this job. You can still apply, will let you know once there is any referrer available.