Senior NLP Scientist

The ideal candidate has deep understanding of NLP, specifically with named entity recognition, word sense disambiguation, entity relations extraction, preferably with experience in the biomedical or clinical domain, and is passionate about genomics and its application to find cure to cancer or cardiovascular diseases.

What You Will Do:

Work with a stellar team of data scientists and engineers working with large corpuses of health records from variety of sources.
Design innovative and generalized machine learning solution to extract critical clinical and genomic entities from unstructured texts in patient records.
Think scale and near human level accuracy.
Devise unsupervised methods to help expand the set of truth labels.
Employ statistical means and knowledge bases for purpose of data validation.
Design and deploy model into scalable and extensible automation data pipeline.
Provide clear measurement metrics on model performance, actively monitor and update model to maintain high performance metrics.
Analyze large volumes of text at scale.
Stay up to date with latest development in NLP space.

Required Qualifications:

PhD, Masters with 3+ years or Bachelor with 5+ years experience in a quantitative or computational field such as Computer Science, Machine Learning, Statistics, Biomedical Informatics or related field.
Experience in modern Deep Learning and Natural Language Processing (NLP) techniques and frameworks, including Transformers, seq2seq with attention, RNNs, gensim, fasttext, spacy, scikitlearn, pandas
3+ years of programming experience in Python.
Proficiency in frameworks like Pytorch, Tensorflow, or Keras.
Experience building production-ready NLP systems.
Strong programming skills, familiarity with software development cycles, solid understanding of software concepts - data structures and algorithms.
Thrive in a fast-paced environment and willing to shift priorities seamlessly.
Experience with communicating insights and presenting concepts to diverse audiences.
Team player mindset and ability to work in an interdisciplinary team.
Passionate to make a positive impact in healthcare.

Preferred Qualifications:

Understand how to leverage word embeddings, skill with word sense disambiguation.

Experience taking to production models in Text Classification, Named Entity Recognition, relation extraction, unsupervised and supervised ML methods, understand trade offs between classic and SOTA Transformer models.

Understand BERT architecture and its variants, experience with huggingface framework

Working knowledge of AWS, GCP, Spark, data warehousing.

Experience using biomedical knowledge information systems, such as UMLS, SNOMED CT, and RxNorm

Publications in SIGIR, CIKM, ACL, AAAI, KDD, EMNLP, ICML, ICLR, NeurIPS or equivalent.

Clinical/Healthcare domain experience especially in Cardiovascular diseases is preferred.