Data Scientist (SWE II)- R&D

About Us
Swvl is a revolutionary idea that was born from passion, loyalty, and persistence to face all challenges that come our way. It started with an observation turning into a realization; too many cars on the streets, wasting our limited resources: time, space, and money.
In 4 years Swvl became the first 1.5 billion unicorn in the Middle East to list on NASDAQ and currently the 2nd best-funded startup in the MENA region. With a presence and operations in up to 10 countries worldwide and a vision to be active on 6 continents.
Our main goal is not just to facilitate commuting, but a hunger to strive for solutions, encourage the contribution of youth in innovation, and inspire change.
We are looking for an engaged and enthusiastic Engineer to join our team of talented engineers that share a common interest in distributed systems, their scalability and continued development.
About the role
We are looking for a driven individual to work in the organization?s Central Analytics Planning team, driving positive growth across the supply and demand aspects of the business. In this role, you will have the opportunity to drive our user behavior and organize the shape of supply to cater to the right demand. This role requires you to mine and analyze data from company databases to drive optimization, implement smart business strategies and improve product development and marketing techniques. The role is inherently cross-functional: You will work closely with a high-energy team consisting of software engineering, data analytics, user experience, device marketing, customer service, and executive team members.
What you will be doing:
? You will be responsible for building, deploying, and monitoring predictive and machine learning models that leverage SWVL data to improve our customers and captains experience and solve SWVL core AI business problems.
? You will collaborate with business and technical stakeholders through the end-to-end data science process, starting from understanding business problems, different data sources, and setting KPIs, to collecting, cleaning, and analyzing data till model deployment.
? You will collaborate with Engineers to transform POC to production level while ensuring models scalability, observability, robustness, and accuracy.
? You are expected to be up to date with state of the art machine learning methods and techniques.
What You Will Need
? Bachelor or Master's degree in CS, CE, ML or 2+ years of industrial experience in machine learning.
? Experience applying methods from supervised and unsupervised machine learning to real-world problems.
? Solid understanding of industrial mathematics and statistics.
? Solid understanding of best practices in feature extraction, dimensionality reduction, model validation, and classification.
? Hands on experience with SQL, Docker, Git, AWS EC2, S3, and Some ML/DL frameworks such as Tensorflow, Keras, Pytorch, XGBoost, Scikit-learn, Statsmodels, PyMC3.
? Proven track record of successful production machine learning models.
? Experience with machine learning lifecycle platforms (i.e. mlflow) is a plus.
? Knowledge of distributed storage and processing of big data is a plus (Hadoop, Spark, etc.).
? Experience in AI system design is a plus.
? Experience in Reinforcement learning is a plus.