Senior Applied Scientist


Contacts:

Job description / Role

Employment: Full Time

About G42

Based in Abu Dhabi, UAE, G42 is on an ambitious mission to empower care outcomes, clinical operations, and clinical R&D through meaningful use of data and AI. We are leading the world’s largest population genome program (www.pgp.ae/) with a goal of 1M whole genome sequences. Through our subsidiary health information exchange company called Malaffi, we are also enabling clinicians with access to patient records from healthcare providers across the emirate of Abu Dhabi. Our efforts in healthcare are powered by our own secure Abu-Dhabi based cloud, which includes Artemis supercomputer (ranked in top-40 supercomputers across the world), and our fundamental AI research arm called Inception Institute of AI. We employ more than 100 PhDs with expertise in AI and different domains, including healthcare. At G42 healthcare our decision-making is guided by seasoned professionals who have been physicians as well as hospital administrators.

Job Description

We are looking for a Senior Applied Scientist – NLP with extensive experience or strong interest in healthcare. You will collaborate with SMEs in data science and medicine. This is an individual contributor position.

What you will do:

Research and understand ways in which NLP is bringing value to healthcare stakeholders from providers, payers, patients, pharma, regulators, and others.

Be the subject matter expert in Natural Language Processing within Healthcare ML.

Technically lead the projects in NLP and health data science.

Develop deploy-ready ML models.

Understand client requirements.

Keep up with the literature in NLP and Health ML.

Review the literature to support development of new business cases in healthcare ML.

Present proposals, plans, and technical material to wide variety of audience from clinicians to board members.

Requirements

Qualifications and Experience:

PhD or MS in NLP, Computational Linguistics, Information Retrieval, Computer Science, Machine Learning, AI, or a related area with strong grasp of ML methods for structured and unstructured data.

2+ years of post-PhD or 4+ years of post-MS work experience.

Depth in at least one of the following NLP domains: Text Classification, Information Extraction, Syntactic / Semantic Parsing, Language Modeling, Text Summarization, Question Answering, Machine Translation, Language Generation.

Awareness of the modern ML literature including Transformers and graph ML.

Fluency in the usual: python, pytorch, tensorflow, sklearn, pandas, etc.

Fluent in at least one NLP library: nltk, spacy, textblob, sparknlp, allennLP, corenlp, huggingface, genism, or similar.

Working comfort with software development tools such as git, docker, bash scripting, etc

Comfortable with text processing (strings, regular expressions, web scraping).

Ability to implement and evaluate NLP models from literature, train and adapt off-the-shelf models to a new domain / language.

A strong enthusiasm for learning new things is essential for success in these roles. Further, we believe teams win and fail together– essential that you are willing to learn from/teach others.

An interest in healthcare.

Good to have:

Understanding of healthcare IT infrastructure and tools including DICOM, HL7, FHIR, etc.

Experience working with domain ontologies such as SNOMED-CT, ICD9 &10, RxNorm, MeSH, etc.

Experience with clinical NLP / bioNLP tools, datasets, software (e.g. biobert, scispacy, jsl)

Familiarity with Spark, SQL

Familiarity with Multimodal Models: text/images, text/speech, etc

Benefits

Highly competitive tax-free salary.

Excellent perks – great health insurance for family, annual flight allowance for family, education allowance for children, 25 business-days annual vacation, company-sponsored visa for family, relocation allowance, gratuity, paid parental leave +more.