Data Scientist (Machine Learning &Bioinformatics)

If you do not hear from us within 10 business days, please understand that we were unable to find a suitable opportunity for you at this time.

About Craif株式会社

Craif Realizing a society where people can live out their natural lifespan — changing the future of medicine, starting with cancer, humanity’s greatest challenge.

Craif is a Bio-AI startup founded in 2018, originating from Nagoya University.

Under the mission of “realizing a society where people can live out their natural lifespan,” the company aims to create a future where lives are no longer cut short by diseases like cancer.

In Japan, it’s said that 1 in 2 people will develop cancer — a challenge humanity has been unable to overcome for over 4,000 years.

Meanwhile, cancer screening rates remain around 40%, meaning many people miss the chance for early detection.

Craif is using technology to overcome these psychological and social barriers, tackling the fundamental challenge of creating a society where everyone can naturally take steps toward prevention and early detection.

Recruitment Background & Career Path Advanced data science expertise spanning both machine learning and biology is essential for improving the accuracy of testing systems like miSignal and developing new methods.

As the business expands, there is an urgent need to strengthen the team with people who can handle everything from model development to operational automation and advancement.

This position seeks someone who can lead omics data analysis and new test system development, driving the creation of clinically valuable models.

In the future, this role can grow into a core R&D career involving architecture design for the entire ML pipeline and planning of new tests.

Responsibilities

• The entire Analytics team operates in English.
• Test System Development & Updates Research design

Analyzing biomolecular data (miRNA, etc.) obtained using

• Craif’s technology for disease differentiation, biomarker selection, and other medical applications
• Publishing research results through academic papers and conference presentations
• Building machine learning models

Setting quality standards and accuracy controls

• Designing and conducting analytical and clinical validation of test systems ML Pipeline Automation & Advancement Collaborating with ML engineers and software engineers to automate the cycle from model development to deployment
• New Method Development Developing new methods for biomarker-based test systems

Requirements

• Japanese is not required for this position.
• Qualifications (Must-Have) Japanese NOT required English proficiency sufficient to work in an international team
• Proficiency in at least one programming language (R, Python, Go, C++) Experience in analyzing omics data, preferably RNA expression data

Foundational understanding of probability theory and statistics

• Foundational understanding of statistical machine learning and pattern recognition
• Experience developing ML models using frameworks such as scikit-learn, Keras, TensorFlow, PyTorch (especially supervised learning for classification problems)
• Research or analysis experience in biology or related fields
• Profile The ideal candidate is someone who strongly aligns with the company’s mission and is proactive and undaunted by the unknown.
• They demonstrate leadership — thinking independently, involving others, and driving projects forward.
• They enjoy working in teams and producing results while respecting diversity, focusing on what truly matters regardless of age or title.
• They are motivated to solve social issues, possess strong hypothesis-building and abstract thinking skills, and are quick to test and validate ideas. ※We will carefully review your application and contact you only if we believe we can offer you a suitable position.

Preferred

• Qualifications (Nice-to-Have) Basic Japanese language skills for casual communication with other team members.
• Development Tools Docker Workflow management languages (Snakemake/Nextflow) AWS cloud ML Experience Training on small-size datasets
• Handling imbalanced data
• Related Domain Knowledge / Experience Transcriptome analysis experience
• Liquid biopsy knowledge/experience microRNA knowledge cfDNA knowledge
• Foundational understanding of next-generation sequencing and quantitative PCR Biological research/analysis experience
• Wet lab experiment experience
• Cancer biology/medical knowledge or analysis experience
• Molecular diagnostics domain knowledge
• Clinical application of machine learning knowledge/experience