Project Sapiens logo

Back End Software Engineer

full-time Project Sapiens London

What should you eat to be healthier? We are combining science, large scale data and machine learning to tell you what to eat based on your unique metabolism.

Join us in tackling wide-ranging technical challenges from DNA analysis, to machine learning, to building products for web scale. We are a well-funded new start-up from a team that has built billion-dollar revenue businesses from scratch, beaten Google on its home turf of machine learning for advertising, and includes some of the 1% most cited scientists in the world.

We are going to generate terabytes of health data from our own clinical studies and direct consumer engagement. We will design and build systems first to collect, store, analyse and predict this data, then to help customers understand and follow their evolving personalised nutritional recommendations. We are building our data processing and analysis pipeline from scratch with Python data science / machine learning toolkits running on top of AWS and following an agile development approach with Jira, daily stand-ups and git.

The role

As a software engineer, you will:

  • Design & build the databases and analysis pipelines which support our models
  • Be responsible for the underlying compute and storage infrastructure on AWS
  • Manage our trial and customer data, and their processing
  • Help our data science / machine learning experts design the models
  • Design & build simple web applications to support data collection from our clinical trials
  • Later design & build the scalable back-end for our mass market products

Key skills

  • Top intellectual capability – we are looking for the smartest and best
  • Ability to move fast, get things done and make stuff happen, working in a close-knit team
  • Degree/PhD in Computer Science, Data Science, Mathematics or Physics
  • 5+ years’ experience building robust, reliable data management and processing systems
  • Experience with Python data science / machine learning toolkits, e.g. pandas, NumPy, SciPy, scikit-learn, Jupyter, Matplotlib, TensorFlow
  • Experience with Linux data infrastructure, e.g. AWS, SQL, Docker, Ansible
  • Experience with Python server-side frameworks, e.g. Django, Flask
  • Ability to work closely with data science / machine learning experts and bioinformaticians

What we offer

  • The opportunity to make the world healthier, and have fun learning about cutting-edge science across biology and genomics
  • An exciting early-stage start-up environment, without the funding worries, and with a commercial team that has built billion-dollar revenue businesses
  • A crucial role as one of the first ten colleagues in a truly world-class multidisciplinary team
  • Competitive salaries and share options
published: Nov. 21, 2018

Apply for this position