We are looking for a senior software engineer to join the forecasting domain within the data science team. The team has previously realized multiple solutions and needs a new system based on the learnings of all previous failures and successes.
The team will jointly built a new solution on the Google Cloud Platform and enable multiple Data Scientists to train and deploy forecasting models simultaneously. The system will consist of two separate parts, one to train and evaluate models and one to apply models to produce forecasts which are used by various systems and users. The training part will consist of a robust outer “shell” to manage infrastructure and repeating tasks (eg collecting data, running scripts, storage of results) and an inner sandbox for the data scientist to experiment and develop models. This inner sandbox will need to be running Python and support multiple projects/users at the same time.
You will join the Data Science squad of Forecasting & Sourcing. The squad consist of both engineers and data scientist allowing you to directly cooperate with your end user. You will have a shared responsibility for the resulting product. We are working with a KanBan setup, allowing fast iteration and low overhead in for instance of user story writing. We also have support of both software and business architects to help design the system and remove impediments.
This availability is also required as we expect the design to continuously update. We are looking for someone who is comfortable with change and agility and likes to continue building on the learnings of the process. We need someone who understands the result we require and will engage with and challenge the users to build this understanding.
Technology experience
The team will jointly built a new solution on the Google Cloud Platform and enable multiple Data Scientists to train and deploy forecasting models simultaneously. The system will consist of two separate parts, one to train and evaluate models and one to apply models to produce forecasts which are used by various systems and users. The training part will consist of a robust outer “shell” to manage infrastructure and repeating tasks (eg collecting data, running scripts, storage of results) and an inner sandbox for the data scientist to experiment and develop models. This inner sandbox will need to be running Python and support multiple projects/users at the same time.
You will join the Data Science squad of Forecasting & Sourcing. The squad consist of both engineers and data scientist allowing you to directly cooperate with your end user. You will have a shared responsibility for the resulting product. We are working with a KanBan setup, allowing fast iteration and low overhead in for instance of user story writing. We also have support of both software and business architects to help design the system and remove impediments.
This availability is also required as we expect the design to continuously update. We are looking for someone who is comfortable with change and agility and likes to continue building on the learnings of the process. We need someone who understands the result we require and will engage with and challenge the users to build this understanding.
Technology experience
- Java (10+ years)
- Python (deploying and running, using to a lesser extend)
- Git (both for the system as a whole and support within the projects)
- Google Cloud Platform / Beam is preferred
- Experience in the setup and design of new systems
- Affinity with Data Science and Big Data analytics
- Clear/transparent in communication
- Open for change and comfortable working with altering roadmaps
- Takes initiative, pro-actively wants to understand needs
- Teamplayer, takes responsibility about achieving results as a team
- Fluent in English and accustomed to working with multi-disciplinary teams
- Can coach other team members and transfer knowledge and expertise