Data Scientist

MiRXES is a Singapore-headquartered molecular diagnostic company with R&D, manufacturing, and clinical lab operations in Singapore, USA, Japan, and China. We specialize in microRNA technologies and the development, manufacturing, and provision of diagnostic test kits and clinical services. Our mission is to enable early disease detection and provide insights for better patient care by harnessing the power of microRNA to augment traditional testing. Our vision is to be the world's leading developer and provider of accurate, actionable, and affordable microRNA-powered diagnostic tests.

Job Summary:

The Data Scientist will lead data science, bioinformatics, and machine learning projects to support the development of cancer diagnostic products. This role will analyze in-house clinical and molecular data to identify biomarkers, develop diagnostic models, and generate insights that guide project design, assay development, product development, and clinical study strategy.

Roles and Responsibilities

• Lead data analysis and machine learning projects for cancer biomarker discovery and diagnostic model development using in-house multi-omics and clinical datasets.
• Identify novel DNA, RNA, and ncRNA biomarkers and develop multi-marker diagnostic models for cancer detection.
• Develop analytics workflows for data processing, quality control, model training, validation, and performance evaluation.
• Support the development of AI capabilities, including medical image analysis where relevant, such as CT and X-ray model development.
• Work closely with clinical, assay development, product development, and commercial teams to provide data-driven insights for project direction and product strategy.
• Lead and mentor data scientists and bioinformaticians, providing technical guidance, project planning, and knowledge transfer in AI, machine learning, and statistical analysis.
• Improve data literacy within the R&D team and support the use of data-driven decision-making across projects.
• Provide statistical and analytical input for experimental design, process optimization, assay quality control, and product validation.
• Support scientific communication, internal reporting, external collaborations, and selected commercial activities when required.

Desired Skills and Competencies:

• Master's degree or PhD in Data Science, Computer Science, Bioinformatics, Computational Biology, Biomedical Engineering, Statistics or a related quantitative discipline.
• Preferably 2–5 years of relevant experience developing machine-learning or deep-learning models for biomedical, healthcare, genomics or life-science applications. Strong candidates with relevant postgraduate research experience may also be considered.
• Demonstrated experience working with high-dimensional biological or clinical datasets, preferably including blood biomarkers, genomics, sequencing data or biomedical images.
• Hands-on experience taking ML projects through the full workflow, including data preprocessing, feature engineering, model development, validation, performance evaluation and interpretation.
• Strong proficiency in Python for scientific computing and machine learning.
• Strong practical experience with PyTorch and development of deep-learning models.
• Proficiency with scikit-learn and conventional machine-learning/statistical approaches such as logistic regression, random forests, gradient boosting, SVMs, clustering, dimensionality reduction and feature-selection methods.
• Experience developing and evaluating deep-learning architectures such as CNNs, transformers, attention-based models, autoencoders or other modern neural-network architectures.
• Experience applying machine learning/deep learning to at least one of the following:- Biomedical image data, including image preprocessing, augmentation, feature extraction, segmentation, classification or representation learning.
• Next-generation sequencing data, including analysis of sequencing reads and/or derived genomic features for classification, biomarker discovery or predictive modelling.
• Familiarity with relevant genomics/bioinformatics data formats and workflows, such as FASTQ, BAM/CRAM, VCF and genomic feature matrices, would be advantageous.
• Good understanding of model validation and statistical methodology, including train/validation/test separation, cross-validation, prevention of data leakage, class imbalance, hyperparameter optimization and assessment of model generalizability.
• Ability to assess diagnostic models using appropriate metrics including ROC-AUC, sensitivity, specificity, precision/PPV, NPV, calibration and confidence intervals, rather than relying solely on model accuracy.

This position is based in Singapore.

We appreciate your interest in the above-mentioned position, however, only shortlisted candidates will be contacted.