Data Scientist at Engie Africa

Job Purpose/Mission

• This position will be part of the Global Data team. This is an incredible opportunity to join a high-performing team that is passionate about pioneering expanded financial services to off-grid customers at the base of the pyramid. Key responsibilities will include building and maintaining data models to support sales and customer finance operations. You would also be involved in data mining activities as well as engage with internal business stakeholders in realtime to our field team mobile application to allow data-informed decisions to be made in the field, as well as working with members of the data team to ensure high code quality and database design. Your work will make a meaningful impact by enabling Engie to continuously innovate on how we support our customers in their repayment journey. Key Competencies

Responsibilities

Data Mining (20%):

• Design and implement robust data mining models to support analytics and reporting requirements.
• Carry out pre – processing, cleansing, and validating the integrioty of data to be used for analysis
• Enhance data collection procedures to include all relevant information for developing analytic systems.

Statistical modelling (70%)

• Use statistical and machine learning techniques to develop solutions to support business operations from sales to credit collection.

Stakeholder management (10%)

• Communicate results with stakeholders within the business operations teams.

Experience:

• 5+ years of industry experience working on data scientist with a focus on data modelling, stakeholder management and data mining.,
• Proficiency using machine learning frameworks like keras, pytorch, Tensorflow, sckit-learn, statistical tools (statistical tests, distribution, regression, maximum likelihood estimators, strong math skills (multivariate calculus, linear algebra), machine learning methods (k-Nearest Neighbours, Naive Bayes, SVm, Decision forests), Data visualization tools (matplotlib, d3.js, Tableau).
• Experience working with structured and unstructured data using Python, R, Scala, Java, SQL in addition to one or more of Spark/Hadoop/Hive/HDFS , Apache Airflow, RabbitMQ/Kafka, Spark, Kubernates, and dbt.
• Working knowledge of databases, data systems, and analytics solutions, including proficiency in SQL, NoSQL, Java, Spark and Amazon Redshift for reporting and dashboard building.
• Experience with implementing unit and integration testing.
• Ability to gather requirements and communicate with stakeholders across data, software, and platform teams.
• Deep understanding of data structures, data modelling and architecture.
• Experience managing a team of mid-level data scientists.
• Sense of adventure and willingness to dive in, think big, and execute with a team

Qualifications:

• Bachelors or master’s in computer science, machine learning, or related field

Language(s):