Principal Data Scientist - Machine Learning For Genomics

About the Role

Our client, a renowned research and development institute based in **Stellenbosch, Western Cape**, is seeking a highly accomplished Principal Data Scientist with a specialization in Machine Learning for Genomics. This pivotal role involves developing and deploying advanced analytical models to uncover insights from massive genomic datasets, accelerating our understanding of complex biological systems and diseases. You will work at the forefront of bioinformatics, leveraging cutting-edge ML techniques to analyze DNA/RNA sequencing data, identify genetic markers, and predict disease risk. This hybrid position allows for a flexible work arrangement, combining on-site collaboration with remote work capabilities. The ideal candidate possesses a deep understanding of both machine learning algorithms and genomic data structures, coupled with a proven ability to translate complex scientific questions into data-driven solutions. This is an unparalleled opportunity to make significant contributions to the field of precision medicine.

Key Responsibilities

• Design, develop, and implement advanced machine learning models for genomic data analysis.
• Extract, clean, and transform large-scale genomic datasets (e.g., WGS, WES, RNA-Seq).
• Perform feature engineering and selection relevant to genetic variations and biological functions.
• Build predictive models for disease association, patient stratification, and treatment response.
• Collaborate with geneticists, biologists, and bioinformaticians to define research objectives.
• Evaluate model performance and ensure robustness and reproducibility of results.
• Stay current with the latest advancements in machine learning, deep learning, and computational genomics.
• Communicate complex findings effectively to both technical and non-technical audiences through reports and presentations.
• Contribute to the development of data analysis pipelines and infrastructure.

Requirements

• Ph.D. in Data Science, Computer Science, Statistics, Bioinformatics, or a related quantitative field.
• Minimum of 7 years of experience in data science, with a strong emphasis on applying machine learning to genomic or biological data.
• Proven expertise in developing and deploying machine learning models (e.g., deep learning, SVMs, random forests, Bayesian methods).
• Proficiency in programming languages such as Python or R, and extensive experience with relevant libraries (e.g., TensorFlow, PyTorch, Scikit-learn, Bioconductor).
• Strong understanding of genomic data types, formats, and common analysis pipelines.
• Experience with cloud computing platforms (e.g., AWS, GCP, Azure) for large-scale data analysis.
• Excellent analytical and problem-solving skills.
• Ability to work independently and collaboratively in a hybrid work environment.
• Strong written and verbal communication skills.

Benefits

Our client provides a competitive salary, comprehensive health and retirement benefits, and opportunities for significant professional development and conference attendance. The hybrid model offers excellent flexibility. Located in the picturesque **Stellenbosch, Western Cape**, the position provides a stimulating research environment combined with a high quality of life. We offer access to cutting-edge computational resources and foster a culture of innovation and scientific rigor. Join a team dedicated to advancing genomic research through data science.

#J-18808-Ljbffr