Java / Python / SQL / Tableau / Decision Trees / matplotlib / Zeppelin / Random Forest / Elastisearch
About Distilled SCH
Distilled SCH is the combined business of Irish owned Distilled Media Group and Schibsted Media Group from Oslo. Together we command leading positions in real estate, motors and general buy and sell with our hugely popular online marketplaces Daft.ie, DoneDeal.ie and Adverts.ie.
What’s the opportunity?
We are looking for a Data Scientist that will work on the creation of the next generation data products for our classified media business. The primary focus will be on choosing optimal techniques and algorithms to use for these purposes; building prototypes and bring them to production.
The Role
What will I be doing?
Key Responsibilities
- Design and implement novel internal and external facing data solutions.
- Provide technical leadership in machine learning and data science to the team.
- Collaborate across teams to build robust services.
- Explore use cases of external data sources.
- Mentor junior members of the team.
- Participate in the wider Schibsted community particularly in the areas of data science, motor and property verticals.
Operational Responsibilities
- Support the construction of machine learning pipelines.
- Extensive validation of models and presentation of results.
- Contribute to the continual improvement of our data platform.
- Conduct code reviews ensuring development follows best practice.
- Liaise with product/design/tech to ensure optimal products are delivered.
What skills do I need?
What skills do I need?
- Excellent understanding of machine learning techniques and algorithms e.g. kNN, Random Forest, Decision Trees, etc.
- Excellent statistical skills.
- Experience with working with notebooks – Zeppelin, Jupyter, etc.
- Experience with data visualisation tools such as ggplot, matplotlib or D3.js.
- Experience building actionable dashboards in BI tools such as Tableau.
- Strong Python/Java, AWS (EC2, EMR, S3, RDS, ElasticSearch, Data Pipeline, EBS etc.), SQL, R and Linux skills.
- Experience working with diverse data sources, including both structured and unstructured data.
- Experience with SQL and NoSQL datastores. Postgres with PostGIS, Redshift and ElasticSearch a bonus.
- Comfortable with container-based software deployment and management (OpenShift, Kubernetes etc.).
- Comfortable with continuous integration services to build and test software projects hosted at GitHub (e.g. Travis, Jenkins).
- Experience working within an agile team environment with kanban or scrum methodologies.
- Comfortable multi tasking or focusing on larger projects.
- Excellent problem solving skills and communicationskills.
- Minimum Masters degree in Computer Science or related technical field.
Start Date
1st March 2018
