Log in

Data Science and Machine Learning Fellowship - Climate Risk Lab, Cape Town

The Climate Risk Lab invites applications from recent PhD, MSc and first-class Honours graduates with backgrounds in data science, machine learning, computer science, mathematics, statistics, econometrics, engineering, physics or related fields. Candidates should be enthusiastic about applying their expertise to climate science and solutions.

Applications are particularly encouraged from historically underrepresented groups in these fields, including female-identifying people of colour.

The Climate Risk Lab’s mission is to develop breakthrough science, tools and policies to protect people and nature from climate change. Current projects include modelling past and future climate impacts, as well as using AI to synthesise evidence on effective climate solutions for human health and wellbeing.

The fellowship aims to strengthen the Lab’s research capacity while developing fellows’ research and data science skills. Fellows will support an interdisciplinary team working with climate, environmental, health and socioeconomic data. They will also be encouraged to lead a project that is meaningful to them.

Each fellow will receive mentorship from a senior data scientist or postdoctoral researcher, with opportunities to lead data-intensive research and participate in working group meetings with international collaborators and/or conferences.

This is a full-time, one-year fellowship based in Cape Town, with the possibility of a further one-year renewal, subject to performance. There may also be opportunities to transition to a PhD scholarship or postdoctoral funding.

Responsibilities

  • Analyse large climate, environmental, health and/or socioeconomic datasets.

  • Develop and apply AI tools to improve data science workflows, and support other analysts in using these tools.

  • Download, clean, process and optimise large datasets.

  • Promote best practices for reproducible workflows, including contributing to and maintaining Git repositories.

  • Document and communicate workflows.

  • Develop and maintain code for efficiently processing and analysing large spatiotemporal datasets, including through parallel computing.

  • Lead or co-lead a research project towards a peer-reviewed publication, toolkit or dataset.

  • Be available for international travel if required.

Minimum requirements

  • An MSc or first-class Honours degree, completed or in the final year, in data science, machine learning, computer science, mathematics, statistics or a related field.

  • Proficiency in programming, preferably in Python or R.

  • A solid grounding in statistics and/or data science principles.

  • Excellent written and verbal communication skills.

Desirable experience

  • Experience with R and Python packages such as xarray, pandas, NumPy, Zarr, netCDF4, terra, tidyverse, Arrow or DuckDB.

  • Familiarity with Bash, Linux and high-performance computing environments.

  • Experience with agentic AI tools.

  • Experience using GitHub for code sharing and collaboration.

  • Experience working with large spatiotemporal datasets.

Application documents

Please submit the following as a single PDF file:

  • A CV stating whether you hold a valid South African work or study permit, and including the names, positions and email addresses of two professional referees.

  • A cover letter explaining your suitability for the fellowship.

  • Your academic transcript.

  • Links to GitHub repositories, Jupyter notebooks or other examples of your code (optional).

  • A link to your personal website and/or LinkedIn profile (optional).

Application process and timeline

Applications will be accepted on a rolling basis through the online application form. Initial reviews will begin in October 2026, with a preferred start date of February 2027.

Shortlisted candidates will be invited to a technical interview. The position will remain open until filled.

Remuneration

Remuneration will be competitive with academic and market rates and will reflect the successful candidate’s experience.

Enquiries

Please contact Puja Pande at puja.pande@uct.ac.za.