Data Scientist

Job Description

• Exploratory Data Analysis (EDA) to gain more insight into Pitik’s chicken farming data.
• Train predictive models that support Pitik’s business processes.
• Validate hypothesizes and answer questions from Pitik’s stakeholders using the data and models.
• Communicate with Pitik’s stakeholders at all levels regarding the development and results of the data analysis and predictive models.
• Perform model optimization for deployment purposes.
• Together with data engineers, build end-to-end Data and ML pipeline for automated dashboarding and model updates.

Requirements

• Strong problem-solving skills, analytical skills, and inquisitive mindset.
• Self-starter and willing to get hands dirty in learning and building ML models.
• Team spirit; strong communication skills to collaborate with various stakeholders.
• Skills in data acquisition (e.g. SQL, Elastic Query, web scrapping) and data integration (joins, fuzzy matching) in noisy scenario.
• Knowledge of proper data preprocessing steps for descriptive and predictive analysis.
• Experience in data visualization; experience using the relevant BI Tools (e.g. Metabase, Looker, Superset, or Tableau) is a plus.
• Experience in predictive models (classification, regression, and time series) using several options of algorithms from the classics (e.g. naive Bayes, zdecision trees, SVMs), boosting, and neural networks.
• Knowledge of model interpretability
• Proficiency in Python and experience in using the relevant libraries (e.g. Pandas, Numpy, Scikit-Learn, h20, Pytorch/TensorFlow).
• Experience in meta-learning algorithms (e.g. TPE) and the tools (e.g. Optuna, Hyperopt, or PyCaret) is a plus.
• Knowledge of data pipeline engineering and experience in the relevant tools (e.g. Airflow, dbt, data warehouses) is a plus.
• Bachelor’s Degree in Statistics, Mathematics, Computer Science, Finance, or equivalent.

Send your updated CV to
[email protected]
Subject: Data Scientist_Full Name