US-MD-Elkridge – Currently Remote
FosterThomas, a Mid-Atlantic Staffing and Recruiting Firm, is leading the search for an NLP Engineer for our Client located in Elkridge, MD (currently remote).
Clinical data informatics is in the midst of a data revolution. As clinical data is increasingly stored in electronic formats, the massive data sets they produce have brought us to the threshold of a new era in medicine, one where the data sciences hold the potential to propel our understanding and treatment of human disease. Our client is committed to accelerating the pace at which the world continuously improves healthcare, combining the best of the clinical medicine sciences and the data sciences.
Our client has recently been acquired by a $300M health IT company as their first foray into both ML/NLP, and the commercial healthcare space (they specialize in providing IT dev & ops services for Federal health-related institutions, like CMS, the VA, SSA, etc.). With the new infusion of cash from our parent, we are looking to expand our small but (now) growing team.
The NLP Engineer will work closely with the NLP team and domain experts to leverage OCR and machine learning techniques to develop digitization software for medical record scans.
Be part of a small team, import the latest NLP/ML/Deep learning techniques from industry and academia, design and implement software solutions for a broad range of NLP problems typically found in the healthcare domain.
- Advanced degree in a quantitative discipline, e.g., Mathematics, Linguistics, Computer Science
- 2+years industry or academic experience in applied NLP a must
- Demonstrates proficiency with:
- Java and Python
- OCR libraries such as Tesseract, PyOCR, OpenCV, .NET OCR SDK, etc.
- Extracting, cleaning, preprocessing data sets. Familiarity with NumPy and Pandas
- Supervised and unsupervised machine learning techniques. This includes regression models, decision tree models, clustering, and deep learning. Hands-on experience with Scikit-learn, Tensorflow, Keras, or PyTorch
- Data visualization and performing model diagnostics. Understand learning curves, work with tools such as Matpoltlib, Tableau, etc.
- Familiarity with rule-based NLP, including CFG, constituency and dependency parsing, as well as their statistical variants. Experiences using NLTK, spaCy, or Stanford NLP
- Specialization in OCR is strongly preferred. Understanding of Transformers, ELMo, BERT is preferred but not required
- Experiences with healthcare industry practices and medical coding a plus, but not required
- Excellent interpersonal, verbal and written communication, and organizational skills - must be able to communicate fluently in English both verbally and in writing
- Should be extremely facts and data oriented.
- Should be deadline and closure oriented.
- Strong persuasion, facilitation and influencing skills.
- Should be self-driven.
- Strong analytical, organizational and project management skills.
- Demonstrated ability to lead and work with cross functional teams including senior level individuals.
- Must be able to thrive in a fast-paced, rapidly evolving environment with varying priorities, based on a team building culture.