This is a unique opportunity to join the fast paced and innovative Computer Science Team at Nuritas. If you think you fit the role, please send your CV to [email protected]
Nuritas is an artificial intelligence biotechnology company revolutionising the discovery of novel, natural and scientifically proven active peptides that can manage and improve human health.
One of the highlights of working at Nuritas is the tight feedback loop between the data team and the R&D team working in the wet lab. This role sits at the interface of the data team and R&D team and is crucial to making experimental findings available to the state-of-the-art Nuritas NPiPhi AI system.
Proteomics and peptidomics are key to unlocking the vast universe of peptides available to Nuritas.
First and foremost, you will take raw data from our orbitrap mass spectrometers and process this data to make it available to our data science team. You will work closely with the lab scientists, analysing large data sets coming from proteomics, delivering insights and helping to make decisions using your data science skills. In addition to this, you will build scalable, interactive solutions to help scientists answer questions from the data. You will also work closely with machine learning experts to help design the next generations of our machine learning models using inspiration from your analyses and/or unstructured machine learning methods.
Responsibilities and duties
- Running a large real-time proteomics data processing pipeline
- Performing analysis of complex big-data/’omics experiments e.g. proteomics, transcriptomics, or quality control to help R&D, manufacturing, and operations teams make decisions on Nuritas’ best disease treating/preventing active peptides
- Design and execution of interactive visualisations and dashboards for both technical and non-technical members of other departments
- Distil questions from the lab and operations to mathematical, programmatic or data viz solutions and help identify opportunities to improve our processes
- Master’s Degree or PhD in Computational Biology, Bioinformatics, Computer Science, Mathematics, Statistics, Physical Sciences, Life Sciences or related quantitative field (or equivalent industrial experience)
- Experience with biological data including any omics. Previous proteomics experience is highly valued
- Familiarity with common Proteomics software tools such as MASCOT, PEAKS, Skyline, MAXQUANT a distinct advantage
- Familiarity with SQL and/or NoSQL database technologies, ideally experience in database design
- Familiarity with one or more programming/scripting languages (Python is preferred)
- Experience with Linux System
- Familiarity with machine learning techniques and python libraries (Scikit-learn, TensorFlow, Keras, Pytorch) is an advantage
- Experience in collaborative software development in python and deployment of web-based solutions for interaction with complex data. Familiarity with web frameworks such as Django, Rails, or Flask is a plus
- Familiarity with peptidomics approaches and data analysis for peptide quantification.
- The successful candidate must also demonstrate strong decision-making, complex problem solving, critical data analysis and interpretation, excellent written and verbal communication skills; and the ability to build productive cross-functional collaborations both within and external to Nuritas computational biology and bioinformatics