Oxford Nanopore Technologies is developing and commercialising a new generation of nanopore-based electronic systems for analysis of single molecules, including DNA, RNA and proteins. The handheld MinION™ device and the high-throughput/high sample number PromethION™ systems are designed to provide novel qualities in molecular sensing such as real-time data streaming, improved simplicity, efficiency and scalability of workflows and direct analysis of the molecule of interest.
The Algorithms Research group at Oxford Nanopore work with cutting-edge machine learning techniques and algorithms to extract the maximum information from our proprietary single-molecule sensing platforms. Our current focus is on the sequencing of biological molecules used for the transmission of information, like DNA, RNA and their modifications, and the complexity of this signal has many parallels with speech recognition and automatic language translation.
We are looking for a highly motivated and numerate individual with strong programming skills to join the Research Division to support our algorithms research. This exciting and challenging role will report to the Principal Scientist leading the group and will be responsible for implementing and developing advanced algorithms for the analysis of biological signals, improving the data analysis for our evolving technologies and opening up new applications.
The team in our Research Division is responsible for researching and developing novel approaches to processing signals from our platform and will be expected to work both independently and as part of the team to achieve its aims. They work across many different applications of our platform, looking at raw, derived and application-specific data to improve our understanding of the platform and open up new uses.
The successful candidate will have worked at cutting edge of their field and demonstrated an ability to research, adapt and improve upon state-of-the-art techniques for processing signals from biophysical data or similar noisy structured systems. They will have spent several years at all levels of the algorithm development chain, from conception to production implementation, and demonstrable experience rapidly prototyping approaches both using available software packages and directly implementing the mathematics from research papers.
Oxford Nanopore Technologies Ltd
The candidate will hold a Ph.D. in a field involving a high level of numeracy, e.g. computer science, engineering, mathematics, physics, or have substantial equivalent experience, and will have experience analysing data from real (noisy) systems. Previous experience working in a time-critical environment with responsibility for reporting progress is desirable.
They will have a broad and deep knowledge of statistical models and machine learning, with knowledge of recurrent neural networks and sequence-to-sequence models being a particular advantage. Demonstrable experience with machine learning frameworks, such as Caffe, Tensorflow, Theano, or Torch, would be an advantage.
The role requires strong programming skills (Python, R, C / C++, etc), both for rapidly prototyping new approaches and producing robust implementations to pass on to the company’s development team. We expect the candidate to have previously produced a significant body of code that has substantial numerical component and to be comfortable moving between languages.
We are looking for an innovative and pragmatic candidate who is keen to learn new skills, be willing to listen and adapt with the changing requirements of the department. They will have good communication and interpersonal skills for explaining complex ideas within the team and to other interested groups.
Please note that no terminology in this advert is intended to discriminate on the grounds of a person’s gender, marital status, race, religion, colour, age, disability or sexual orientation.
Every candidate will be assessed only in accordance with their merits, qualifications and abilities to perform the duties of the job.
How to apply:
Please mention NLP People as a source when applying