The Data Science team at OLX Group is responsible for building algorithmic solutions to facilitate transactions between buyers and sellers. We are developing personalization technologies and optimization strategies that have a direct impact on OLX’s users as well as the company's bottom line. You will be expected to research state-of-the-art machine learning, in the areas of user segmentation, Text mining, image metadata extraction (including multilabel classification and tagging with deep learning), semi-supervised learning, and more. You will apply these methods to core OLX product platforms deployed in the cloud that are affecting the user experience for millions of visitors per month. You will roll your solutions to production, analyze results offline and online, and measure site impact.
What you will be doing:
- As an online OLXAuto/Classified platform, we aim to understand our users in order to help them in their customer journey. Part of this effort includes understanding the different buyer segments and their buying preferences.
- Content(Image/Text) Quality assessment and enhancement with AI.
- Process and Price Optimization for increasing the bottom and topline metrics.
- Your responsibility will be to drive such projects globally from the data science side
- Work on optimizing the models according to the requirements of the specific use case and collaborate with other team members to bring in production and scale machine learning solutions.
- Measure the impact of your models on key metrics of the company.
- Collaborate across the Data Science community to find technical solutions to complex business problems.
- Work in an agile environment to deliver high quality software against aggressive schedules.
Who we’re looking for:
- You are a highly driven, results-oriented, creative problem solver with a hands on approach to deliver business impact quickly.
- You are excited by the opportunity to directly impact the daily experience and happiness of millions of people around the world by matching supply and demand.
- You have a good understanding of machine learning techniques (classification, clustering) and have applied them to solve problems using machine learning libraries such as scikitlearn, scipy, etc
- You have a strong engineering background working with good knowledge of at least one programming language (Preference is Python) as well as engineering best practices.
- Experience writing SQL queries and handling large amounts of data.
- Experience bringing models in production.
- Excellent written and oral communication skills.
- Fluent in English.
- Data Engineers wishing to make the transition to a more Data Science role are welcome to apply as well.
ammatically authoring, scheduling and monitoring workflows (e.g. Apache Airflow).
- Nice to have:
- Industry experience creating and productionizing machine learning algorithms at scale (e.g.,
production use of AWS Athena, AWS Sagemaker, AWS Spectrum, AWS Kinesis) or the GCP
- Experience setting monitoring (e.g., Grafana) and alert notifications (e.g., New Relic), etc
- Experience building large-scale batch and real-time data pipelines with open source data processing frameworks like Spark or Storm.
- Experience with Tensorflow or MXNET.
- Experience with platforms for progress