We are looking for an experienced developer with knowledge of big data development and analysis and a strong interest in machine learning and data science to join our Research & Development team in Montreal. Our R&D team, a.k.a. the Gold-Miners, develops solutions for detecting invalid radio streaming sessions, with a strong focus on detecting the sessions that are not created by humans.
As a Big Data Developer, you will collaborate closely with the Data Scientists to productionalize machine learning algorithms and other analytical methods for detecting invalid traffic. You will also collaborate with the Big Data Developers from the Measurement team, as well as the DataOPS team to create robust and maintainable data pipelines for our invalid traffic detection solutions. Occasionally, you will work with the Data Scientists to carry out advanced analyses using data science methods and machine learning algorithms to enable data-driven decisions at Triton.
You will bring to the team your strong coding skills in PySpark and Python, as well as your excellent communications skills and ability to explain technical concepts to a non-technical audience.
Responsibilities
- Gain understanding of the various data sources and data processes at Triton.
- Perform data wrangling, data validation, feature engineering, and data enrichment tasks to prepare the data for training algorithms, and for feeding the data science experiments.
- Design, develop and maintain data pipelines that enable the R&D work, and deliver the results of the invalid traffic detection to other teams at Triton.
- Gain knowledge of machine learning algorithms and their applications as relevant to the audio streaming business.
- Collaborate with the Data Scientists to carry out advanced analyses, as required by other teams at Triton.
- Prepare technical documentations and presentations.
- Participate in team meetings and technical meetings with other teams.
Qualifications
- BSc or MSc in Computer Science, Computer Engineering, Software Engineering, or a related technical field
- 5+ years of development experience and at least 2 years of experience in big data development
- Experience with distributed systems such as Apache Spark
- Coding expertise in PySpark and Python
- Interest in Machine Learning Engineering/Data Science
- Knowledge of the Agile methodology
- Strong organizational skills and ability to work both independently and collaboratively.
- Strong communication skills in both written and spoken English & spoken French required.