Research Coordinator - Data Science, Climate and Maternal Health: CESHHAR Zimbabwe

Deadline: 20 May 2022 (4.30pm)

Duty Station: Harare, Zimbabwe

Contract duration: 4 years with a review after 6, 12, 24 and 30 months

About

CeSHHAR Zimbabwe is an organisation that specialises in Population health research and programming, including on sexual and reproductive health and HIV / AIDS. CeSHHAR has an extensive national, regional and international academic and community partnership network. CeSHHAR is looking for a candidate to fill the following position starting June 2022.

Job role

CeSHHAR is a partner in the new US National Institute of Health (NIH) funded project, the HEAT Center. The HEAT Center is part of the broader NIH DS-I Africa program, which aims to advance the application of data science to key health challenges in Africa, as well as build data science capacity across the continent. The HEAT Center is focused on the interaction between environmental heat and health, with sub-foci on heat and maternal and neonatal health. Key challenges to be tackled include the integration of complex and diverse health data, with geospatial and climate data (eg satellite imagery, climate model data), in order to advance understanding of the complex interactions between human health, socio-economic conditions (e.g housing, access to services), and weather extremes such as heat waves.

The available Research Coordinator opportunity will be predominantly focused on advancing data science and machine learning methods within the HEAT Center project on Heat and Maternal and neonatal health. In addition, the candidate will contribute to data harmonization, data integration. There is scope and expectation that engagement with a variety of data science projects within the HEAT Center would take place. There is an opportunity to do a three-year funded PhD with LSTM.

Working as part of a team, the Research Coordinator will assist with developing analysis proposals, conducting data analysis (including of a large Individual Patient Data (IPD) database), data management and harmonization, presenting at scientific meetings, drafting manuscripts, data analysis and publication of results.

Qualifications and experience

A MSc in (Bio)Statistics, Computer Science, or related fields; Strong programming skills and experience with Python, R, STATA or similar; Experience providing training in data science methods; Experience working with large and complex datasets (eg. remote sensing, health data, climate model data); Additional skills and experience that would be advantageous include:- Experience working in a JupyterHub environment; Demonstrable experience with Python (or R or STATA) data processing and numerical packages including NumPy, SciPy and Pandas; Demonstrable experience with Python machine learning packages such as scikit-learn, and at least one of the deep learning packages / platforms such as Keras, PyTorch or TensorFlow; Ability and experience working in an international multi-disciplinary team.