Research Scientist, Bioinformatics (AI, Machine Learning)

About the Company

Hummingbird Bioscience is an innovative clinical-stage biotech company focused on developing precision therapies against hard-to-drug targets to improve treatment outcomes. They harness the latest advances in systems biology and data science to better understand and solve the underlying causes of disease and guide development of their therapeutics. Enabled by their proprietary Rational Antibody Discovery platform, they discover antibodies against optimal yet elusive epitopes on important targets that have not been successfully drugged, unlocking novel mechanisms of action. They are advancing a rich pipeline of first- and best-in-class precision therapies in oncology and autoimmunity, in collaboration with global partners in academia and industry. Their highly experienced teams in the US and Singapore span antibody discovery, pharmacology, production and clinical development, aiming to accelerate the journey of new drugs from concept to clinical care.

About the Role

We are searching for an experienced Research Scientist in Bioinformatics who will report to the Head of Computational Biology & Bioinformatics. The ideal candidate will have a strong background in developing bioinformatics code and pipelines for deployment on local HPC as well as cloud-based environments. The role will involve a wide mix of bioinformatics data types including bulk NGS, single-cell and spatial omics data as well as data mining of publicly available datasets. The role will also be responsible for maintenance and development of in-house databases and bioinformatics solutions. This is a key role which will interface with multiple teams across different disciplines. The ideal candidate will have an established track record in the field and possess a broad base of computational skills, a good understanding of omics technologies and applied statistics/machine learning.

Duties & Responsibilities

• Lead and develop the bioinformatics infrastructure of the company.
• Develop and maintain a database of internal data.
• Develop suitable graphical interfaces to rapidly respond to queries from other teams to address the needs of the company.
• Improve existing proprietary bioinformatics tools and algorithms and develop new ones.
• Help to manage in-house HPC, central database and pipeline resources, and cloud-based bioinformatics software infrastructure.
• Support on-going biomarker discovery analyses.
• Support on-going R&D efforts across departments.
• Form an effective cross-functional team with other bioinformaticians and biologists.
• Train company staff in relevant bioinformatics techniques and/or deploy bioinformatics solutions to meet their needs.
• Establishment and maintenance of documentation procedures and configuration profiles.
• Perform other job-related duties as assigned.

Experience and Qualifications

• PhD in Computer Science, Physics, Mathematics, Engineering, Biology, Biochemistry, or other Physical science.
• A strong background in Mathematics/Statistics and Computer science.
• A minimum of 3 years post-PhD experience with demonstrated track record in project management.
• Good understanding of machine learning techniques especially neural networks and deep learning architectures.
• Proficient in R, Python, and Workflow management systems such as Docker, Snakemake, or Nextflow.
• Deep knowledge of Unix style operating systems with experience of utilizing or managing HPC clusters.
• A strong understanding and experience in handling datasets from high throughput sequencing technologies, including Illumina and Oxford Nanopore.
• Demonstrated prior experience of multi-omics data integration to yield novel insights.

Preferred Skills

• Machine learning frameworks such as Spark, Tensorflow, Sci-kit Learn
• Python
• Unix

Good-to-have Skills

• Genomics
• High Performance Computing
• Oxford Nanopore
• R programming
• Sequencing Data