HQ SPAIN (REMOTELY- MAD-BCN-) Data Scientist

You will be part of our Data Science team, called “Labs”, a team formed by 5 Data Scientists, with senior and mid profiles, working on a quite wide set of challenges.
We are looking for a technical profile that is willing to take ownership of key projects from beginning to end (data analysis, business impact, technical solution). Few examples of the responsibilities are:
Take full leadership of a project, being able to start it from scratch and bring it to production synchronizing with other Data and Software Engineers.
You should have a very strong technical understanding of the statistical methodologies to use and how the algorithms work behind the scene.
Being able to brainstorm and collaborate with other colleagues, documenting your project, describing insights and ideas, and keeping up with date stakeholders with sync, slack, and email.
You should be willing to learn and apply very good practices in anything you do, but in particular when writing your code (analysis, features engineering, model training, experiments). We use collaborative tools like Google Collab but we also store our analysis and models in GitHub repositories, to do Pull Request andfine-tunee our code.
Ability to deal with stakeholders (less technical) collecting requirements, and thinking in advance to future needs.
Few examples of projects include:
Work on the Worker Quality Score model of our users and clients, using the various different types of data sources we have to be a fair model that can estimate the performance and the engagement of the users with that specific client environment.
Work on the Candidate Quality prediction, forecasting what kind of performance these new candidates (people that never worked with us) will have for a specific job position.
Work on the Matching Algorithm, improving the Learning-to-Rank model that is combining multiple algorithms to match the best workers and candidates to a given job position.
Work on the scheduler optimization algorithm, a Linear Programming model that is able to find the optimal shifts from a given demand as well as assign the best workers considering their abilities and preferences.
Work on a forecasting model that can predict the upcoming demand of vacancies, estimate if our marketplace already has enough workers for this demand, and in case notify Marketing or other departments.
The Data Team is a quite independent department formed by BI, Labs, and Engineering teams. All the teams work very closely, and we take care of deploying our own models and solutions. This makes us very flexible and able to move quickly to maximize our impact.
Requirements and Skills
Technical degree in Engineering or Quantitative field, a Ph.D. is a plus.
Preferred a mix of experience in both startup and big enterprise environments
Strong theoretical and applied knowledge in Statistics (hypothesis testing, supervised and unsupervised models, etc.).
Strong programming skills with Python and SQL. Any other language is a plus
Experience with NoSQL databases
Strong experience in advanced Data Analysis, data retrieval, cleansing, investigations, etc.
Experience in code collaboration (PR/code review, good practices), CI/CD, monitoring and logging services, and solutions.
Experience in at least 2 of these topics (ordered by importance):
Classification and Regression problems.
Information Retrieval.
Operations Research, in particular with Linear and/or Constraint Programming.
Computer Vision (mainly document detection and recognition).
Natural Language Processing.
A plus, experience with Spark, Apache Hadoop, Airflow.
A plus, experience with ML libraries such as XGBoost, TensorFlow, Or-Tools.

Skills
Python, Git, CI/CD, SQL, Airflow, Hadoop, Data Analysis, Apache Spark, TensorFlow, Computer Vision

Employment type
Full-Time (40h)

Work arrangement
Yes