NLP Data Scientist m/f/d

About ARTIDIS

ARTIDIS AG is a clinical-stage health-tech start-up founded in Basel, Switzerland that has developed the first nanomechanical biomarker for cancer diagnosis and treatment optimization. The ARTIDIS nanotechnology platform integrates different types of clinical data into the ARTIDISNET digital platform, allowing physicians to significantly shorten the current diagnostic process and benefit both the patient and the healthcare system. ARTIDIS enables professionals to design personalized cancer treatment plans tailored to individual patients' needs and desired outcomes.

Job Purpose

ARTIDIS is changing the way cancer is diagnosed and treated. As a member of our team, you will have the opportunity to create products that will assist doctors, clinicians, nurses and patients in conducting clinical studies and providing better healthcare. An NLP Data Scientist at ARTIDIS is expected to communicate and understand customer requirements.

As an NLP Data Scientist, you’ll be tasked to develop, deploy, and NLP models on a medical device and in the cloud.

Duties and Responsibilities

• Develop, productionize, maintain, and improve NLP pipelines and NLP models for PHI redaction and medical text extraction using classical text analytics and deep learning NLP techniques

Qualifications

• Strong interpersonal, organizational, and multi-tasking skills; attention to detail
• High level of expression and comprehension of the English language
• Experience in digital health and driving innovation in health care
• Experience with both classical NLP techniques (tokenization, part-of-speech tagging, stop word removal, pattern matching) and deep learning-based NLP techniques
• Experience developing and productionizing NLP models pipelines
• Experience implementing NLP techniques on medical documents (named entity recognition, span categorization, PHI detection, medical text extraction)
• Experience with OCR libraries
• Experience annotating and developing models with prodigy
• Experience with the Python data stack (spaCy, numpy, pandas, scikit-learn, TensorFlow, PyTorch)
• Experience with cloud-based NLP tools (preference for Microsoft Azure)
• Experience designing architectures and pipelines for NLP-focused applications
• Writing documented, clear and efficient code
• Understanding of how and why to use version control systems for code, data and models
• Ability to design and implement requirements with long-term objectives in mind
• Proactive way of thinking, communicating and working
• Ability to work without supervision

Nice to have:

• Understanding of MLOps and putting pipelines into production (containerization, API creation)
• Understanding regulations in the medical device and software fields (and their relevance to machine learning)
• This position is eligible to be located in any of the following locations:

o Basel, Switzerland

o Houston, Texas

o Fully Remote

Working conditions

The environment is a typical start-up with an intrinsically motivated international team. Our company is an excellent place for rapid advancement and offers a promising opportunity to learn and share know-how in a very agile environment. The position requires the employee to go the extra mile when needed. We are looking for a team player who appreciates direct communication. The effort is rewarded with challenging tasks, the possibility to take responsibility, a highly driven team and work serving a significant purpose. The job position comes with a competitive salary and a bonus for outstanding performance.