Never pay for any CBT, test or assessment as part of any recruitment process. When in doubt, contact us
The SAMRC’s Genomics Platform in collaboration with Environment & Health Research Unit requires a Senior Scientist to carry out data science related activities required for model training, testing and validation. The incumbent will also support the piloting of the two applications of large language models (LLMs) applied to variant emergence/detection, including work such as merging datasets to fine-tune both LLMs against raw metagenome sequence data. The aim of this study is to establish a proof of concept for the integration of wastewater surveillance, metagenomics and artificial intelligence (AI) in disease detection, particularly focusing on its application in the South African context.
Responsibilities:
- Publishing articles in peer reviewed journals
- Substantially contribute to drafting of research proposals.
- Project Management which will include coordination of projects:
- Developing of research tool and SOPs/techniques
- Organization and management of Data
- Quality assurance and ensure adherence to SOPs
- Conduct data analysis and write-up
- Engage with stakeholders
- Research translation
- Work in Linux environments.
- Scripting in Python, C#, Java and R.Processing and Analysis of Next Generation sequencing data.
- Co-/Supervision of 1 master’s student or 5 hours engagement in teaching or training (may be of staff in the Unit) including capacity building of staff, training and technical support provided
- Poster or oral presentations at local or international conferences or at external meetings where own research is presented
- Building bioinformatics networks – both local and international.
Core Requirements:
- Master’s degree in molecular biology, Genetics or a related field.
- At least 2 years research experience in computational and statistical analysis of high-dimensional and multivariate data
- At least 2 years’ experience in Project management and data management
- Presenting research findings and reports at relevant conferences/meetings
- Familiar and up-to-date knowledge of next generation sequencing modalities
- Experience in working in Linux environments.
- Proficiency in common scripting languages (Python, Java and R)
- At least 1 year with next generation sequencing data analysis
Advantageous:
- Registered for a PhD in molecular biology, Human Genetics of a related field.
- Experience with Good Clinical/Laboratory Practices.
- A track record initiation and management of several research projects.
- Comprehensive use of computational clusters for all analytical methods.
- Knowledge of Large Language Models.