Senior Data Scientist

This role will work on some of the most challenging and fascinating problems in transport, logistics, economics, and the space around. You will apply deep learning, geospatial data mining, simulation, forecasting, scheduling, optimization, and many other advanced techniques on our huge datasets to push our business metrics to their bounds, directly and indirectly. Bykea is planning on setting up autonomous data science units focused on different business problems.

Central Platform:

The platform team works on things that cut across the business functions. Developing mechanisms for AB Testing, forecasting, conversational AI and customer services for better customer experience, focusing on the driver network solutions such as facial detection, and working with other central teams like finance and customer services.

Ride-hailing:

You will build algorithms and models to match passenger and driver, to predict time of arrival, to predict when a driver will churn (i.e. stop driving for Bykea) etc. Focus areas will include driver-partner experience, forecasting, maps and routing, marketplace levers, matchmaking between supply and demand, pricing and incentives, customer experience and churn prediction, personalization etc.

Commerce Functions:

For our commerce functions (which include food, grocery, convenience, deals and B2B), the focus of the team would be on search and recommendations, time and route management, text mining and data scraping, natural language processing, forecasting, growth optimization, dynamic pricing and matchmaking and much more

Risk and Fintech:

This team would focus on risk management, customer and driver ‘credit score’ profiling, controls to prevent payment fraud, work on account security, minimise credit risk, marketplace matchmaking, pricing and forecasting amongst others.

Requirements:

1. At least an undergraduate degree from a top tier university
2. Understanding of machine learning, deep learning, data mining, algorithmic foundations of optimization.
3. Experience with machine learning framework (scikit-learn, Spark MLlib etc).
4. Proficient in one or more of the following programming languages: Python, R, Scala.
5. Experience in building ML models at scale, using real-time big data pipelines on platforms such as Spark/MapReduce.
6. Familiar with noSQL, postGIS, stream processing and distributed computing platforms.
7. 3+ years of work experience in data science, data architecture, data modeling, technical solutions, business intelligence, engineering or other technical positions - SQL and Python experience required
8. Excellent quantitative skills and comfort with data stores , ETL & querying frameworks (Spark, Hive)