About the Job
Sandtable is a data science company that creates simulations of human behaviour to support strategic decision making by organisations.
To build insight (understanding why) and foresight (understanding what if) into human behaviour through data analysis and the development of data-driven computational models
- Work closely with the planning team to identify and solve client questions
- Answer client questions by using appropriate modelling techniques on available data
- Conduct exploratory data analysis on a wide range of data sets
Communicate findings clearly
- Drive the collection of new data and the refinement of existing data sources, cleaning, processing and re-organising data as necessary.
- Build data-driven computational simulations to predict and understand behaviour.
- Drive advances in our simulation approach using your experience
Analyse and interpret the results of model-based experiments
- Develop novel metrics for model evaluation and exploration
Work with the visualisation team to design and create engaging and useful applications to explore model output data
Skills, qualifications & experience
- Ph.D. in a physical, biological or engineering science with a focus on applied complex systems modelling.
- 5+ years experience in complex system modelling (e.g. dynamical systems)
- 3+ years experience in building and analysing Agent Based Models (ABM)
- 3+ years experience working with large volumes of real data
Expert programming ability, specifically in Python, C and Java (5+ years)
- High level of expertise in individual-level modelling, specifically numerical approaches to simulation and GPU accelerated computation
- Familiarity with relational databases and SQL (3+ years)
- Experience with machine learning techniques, in particular reinforcement learning
- Experience working with cloud based systems, specifically AWS, and data science tools such as Redshift
- Experience manipulating and analysing dirty, complex, high-volume, high-dimensionality data from varying sources
- An interest in underlying domain problems (not just model mathematics)
- 1+ years building large scale simulations of human behaviour, specifically related to consumer purchasing behaviour, in a commercial setting
- Knowledge and understanding of the structure and dynamics of consumer markets
- Experience building models of consumer choice
Extensive experience solving analytical problems using quantitative approaches
- A passion for empirical research and for answering hard questions with data
- A flexible analytic approach that allows for results at varying levels of precision
- Ability to communicate complex quantitative analysis in a clear, precise, and actionable manner