Data Science Python Developer / Machine Learning Engineer

Job Summary –



In this role, you will:

1. Improve our internal Python library used for model deployments by adding new features, cleaning up code, optimizing performance, and expanding unit testing.

2. Develop our Optimization Library from a proof of concept to a fully standardized tool for deploying optimization.

3. Standardize and streamline the data pipelines used for our forecast models.



Responsibilities:

· Develop a detailed plan for refactoring/optimizing the code in Python while ensuring its functionality and performance are maintained

· Write well-structured, efficient, and maintainable Python code, following best practices and company coding standards

· Thoroughly test the new Python code, identify and resolve any bugs or issues, and ensure the results are consistent with the original implementation

· Create clear documentation for the migrated Python code including comments, user guides, and technical specifications

· Standardize and streamline the data pipelines used for our forecast models in PAT while defining and recommending the team best practices.

· Communicate progress and challenges effectively with the project team and stakeholders



Required Skills:

· A bachelor’s or master’s degree in computer science, Data Science, or a related field

· At least 8 years of experience in a related role

· Knowledge of algorithms, data structures, and best practices in software development

· Strong programming skills in Python and experience with production grade python code

· Deep knowledge of Python libraries such as Scikit-learn, PySpark, NumPy, Pandas

· Familiarity with Python’s unit testing framework (currently using pytest)

· Experience collaborating and using Github

· Excellent communication and teamwork skills, with a strong attention to detail

· Prior experience working with Databricks



Preferred Skills:

· Prior experience with operationalization of ML models

· Prior experience with ML models and collaborating with DS teams.

· Familiarity with R programming language. This role might require to migrate some R code to Python/PySpark.

· Experience with production grade pipelines and ideally with Databricks Delta Live tables or any other declarative pipelines

· Knowledge of pricing algorithms and demand forecasting models