Mendelian is helping doctors diagnose rare genetic diseases faster.
We are looking for an experienced Software Engineer passionate about NLP (natural language processing) who can help us design and deploy production biomedical text mining techniques and help us grow our Spark, Docker, Tensor Flow, Kubernetes infrastructure, as well as exploring and implementing new technologies and frameworks.
Get in touch if you want to play a key role in a high-impact growing startup — and if you are cool with building stuff that save people’s lives. (!)
*About Mendelian Genetics*
We built an online medical search engine supporting physicians in identifying genes that can explain certain rare conditions. Rare diseases (all 7,000 known types combined) affect over 350m people (more than cancer!) and take on average 7 years to diagnose in clinics. The tool is used by thousands of doctors from 140 countries and has attracted acclaim from top researchers and clinical doctors in the field.
Mendelian uses patient’s clinical features to find genes responsible for rare diseases. Mendelian’s intelligent agent parses patient’s phenotypic features entered by a physician and outputs their causative genes and mutations. Thus offering a new way of investigating undiagnosed cases.
The company spun out of Singularity University in 2014 and the larger team met while at Imperial College’s Incubator. It now now comprises a blend of skills and experiences, from Computer Science graduates to MBAs and Health professionals. We are now based in Old Street at the awesome Trampery.
*More about the tech*
Our tech stack is constantly evolving to incorporate new ideas that keep us right on the bleeding edge. Our existing platform is primarily Python but we are advocates of using the right tools for the right job. (#Haskell) Are you willing to take on challenges in building scalable and robust platforms around DNA and big data?
*More on the role*
Biomedical text mining is a research field at the edge of natural language processing and biomedical informatics.
Our current research efforts focus on the enhancement of a Natural Language Processing (NLP) pipeline to automatically identify biomedical entities and extract clinical relationships from vast amounts of text in the literature and in medical reports. Newly extracted relationships are regularly added to our Knowledge Base to improve the accuracy of our search engine.
If you are a talented NLP expert, passionate about solving hard language problems and believe that there is always something new to learn, we want to meet you.
So, wanna play a key role in a high-impact and growing startup? (yeaah!)
Development of state-of-the-art text mining techniques to enable clinical entities recognition and relationship extraction
Keeping yourself up to date with the latest publications in academia and industry
Sharing the knowledge and learning within the team
The ideal candidate will have:
Knowledge of NLP techniques (pre-processing, Named Entity Recognition, entity linking, word embeddings, parsing, etc.) and machine learning (LSTM, etc.)
Experience in dealing with vast amount of textual data (optimization and performance enhancement)
Proficiency in Python or similar scripting language
Ability to drive technical projects autonomously
Really comfortable and opinionated on development tools (Docker, Terraform, Jenkins)
Can put together basic full-stack systems
Familiarity with a scripting language (Python, Bash)
Understands the importance of testing, monitoring and automated alerts
You might know how to bake a good cake? if you do that’d be pretty cool!
Sorry, but we will not sponsor VISAs, brexit or not, please do not apply if you don’t have the right to work in EU.
How to apply:
Please mention NLP People as a source when applying