Senior R&D Data Scientist

We are looking for a Senior R&D Data Scientist to join our Data Science R&D team at Triton Digital. We are using data engineering, data analysis, data science methods and machine learning algorithms to develop innovative solutions for our advertising and audience measurement platforms for podcast and radio. We are analysing vast amounts of data to understand the listeners’ interests in specific podcast shows and radio stations, as well as their listening behaviors across media types and time, to improve the way me measure audiences and target them with specific ads. As a Senior R&D Data Scientist, you will report to the Director of Data Science and will work with the other members of the Data Science team as well as other teams at Triton Digital (including big data developers, POs, PMs) to develop and implement data driven innovative solutions into our advertising and measurement platforms for podcast and radio. Your knowledge and experience allow you to work efficiently from the early, and highly challenging stages of experimentation, all the way to obtaining full-scale data science products ready to be implemented in production through cross-functional collaboration. You will work in an Agile environment adapted to suit the needs of R&D work. You will have the opportunity to work in an industry where creating pioneering solutions to address business challenges will be a part of your daily routine. In our ever-evolving industry, every project requires a collaborative and customized approach that can be transparently validated through extensive exploratory data analysis techniques and easily explained to technical and non-technical stakeholders. Therefore, if you are someone who likes to roll up their sleeves and do the work that needs to be done, who is a good communicator, an enthusiastic team player, who likes to think outside the box and embraces a good challenge this position is for you. Qualifications Minimum education requirement: BSc or MSc in computer science or a STEM field with courses in statistical analysis or other advanced data analysis disciplines. Minimum 5 years of work experience in a business environment using Python, PySpark or Scala, with a minimum of 3 years worked as a main contributor to create, validate and help implement data-driven solutions in PySpark or Scala, where you used advanced data aggregation techniques, statistical methods and ML algorithms. Proven track record of using judgment and decision skills to interpret results, to communicate, and to carry out R&D data science work in a result-driven manner. Proven track record of using exploratory data analysis to understand the input data and the results, and to investigate problems to find the causes and create solutions. Ability to work under pressure, learn continuously and pivot to correct the course of the R&D data science work. Ability to focus on the problem and use creative approaches efficiently from the early stages of a project when there are more unknowns than knowns. Ability to work both independently and collaboratively within the Data Science team and with cross-functional teams. Strong communication and time management skills. Responsibilities Collaborate within the team and cross-functionally to help define the project stages and help select the best approaches at each stage. Collaborate within the team to form hypothesis and plan the experimental work at each project stage. Test and compare different methods and algorithms during the experimental project phases. Produce high quality code in PySpark that is easily reviewed by others and easily incorporated into the project’s data processing pipeline. Produce methodologies that lead to explainable results. Select the most appropriate R&D methodology for solving the business problem at hand, given that black box algorithms might not be suitable most of the time. Perform extensive data analyses on the input data at the beginning of a project to understand its issues, the value of the information that can be extracted from it, as well as its applicability to solve the problem at hand. Innovate to create and validate variables and use them as input data to train machine learning models, create custom logic rules, or a combination of both. Perform extensive data analyses on results throughout the course of a project to validate them, or to debug inaccuracies and create solutions to address them. Iterate quickly by taking decisions based on results to validate or adjust the course of action for the subsequent analysis steps. Prepare results dashboards and presentation materials to explain work progress and outcomes to decision makers, project stakeholders, and during sprint reviews or team meetings. We work with data that presents us with multiple interesting challenges and interesting problems. You will maintain a strong focus on the work priority to solve the problem at hand. Document methodologies and results in systems such as Confluence and Jira. Triton Digital is an equal opportunity employer committed to fostering a diverse, equitable, and inclusive workplace where all employees are respected, supported, and enabled to perform at their highest potential. Our benefits package includes Fully remote position 4 weeks of vacation + 5 paid personal days annually Group insurance programs as of your first day, including access to telemedicine and an EAP Collective RRSP with matching contribution of 4%