Senior Data Scientist - AI

About Mitra bio

Mitra bio is a dynamic start-up backed by Khosla Ventures, Illumina and Oxford University looking to disrupt the skincare industry through data. Mitra is developing a skin longevity platform powered by non-invasive sampling and epigenetics to enhance diagnostics and personalised treatments for the skin.

The Role

You will be working on cutting-edge omics studies to advance skin diagnostics and discovery of novel treatments. Your work will translate into an impactful product in the hands of the consumer. In this customer-focused and technically savvy role, you will deliver data science solutions for Next Generation Sequencing with a focus on DNA methylation. You will work in a multi-disciplinary team and will have the opportunity to be involved in strategy to develop bespoke methodologies and ML/AI algorithms for diagnostics and prediction tool development.

The Responsibilities:

• Build and optimise deep learning models for biological age determination and disease stratification based on large datasets of epigenetic data;
• Build ML/AI models to predict skin phenotypes from epigenetics and comprehensive metadata/clinical endpoints;
• Work with the data team to incorporate other omics into the prediction models to improve accuracy;
• Work with the engineering team to incorporate your models into valuable products;
• Work on the AWS infrastructure (data storage, analysis pipelines, compute nodes and AWS specific user/role/resource permissions);
• Manage multiple projects simultaneously and complete projects in a timely & reliable manner;
• Design and deliver in-depth, and state-of-the-art client reporting on high throughput data generated from various NGS and array data from various domains (specifically epigenomics, but also including genomics, proteomics, etc.);
• Present experimental plans and results to internal and external stakeholders;
• Work as part of a multidisciplinary team;
• Be involved in hiring and team growth.

Essential skills and experience

• MSc or PhD equivalent experience in Bioinformatics, Biochemistry, Computer Science or a related subject;
• 3+ years’ experience delivering bioinformatics and ML-based solutions to the industry;
• Strong experience in software development (mainly Python), test-driven development and proficiency in collaborative software development practices (code reviews, branching models);
• Experience in version control, CI/CD and automated deployment;
• Experience in cloud computing (e.g. AWS/GCP);
• Familiarity with tools used in modern Illumina NGS data analysis;

Desirable:

• Experience in analysis of epigenetics data such as DNA methylation and variant analysis (GWAS) is also advantageous;
• Experience working in agile environments;
• Experience deploying and maintaining secure computing environments;
• Familiarity with research governance, The Data Protection Act and Good Clinical Practice;
• Curiosity on using and implementing current AI technologies into company workflows.