Senior Data Scientist

Senior Data Scientist
Join Us. Let's make a direct impact in healthcare.
Being an Iodine employee means becoming part of something bigger: using clinical AI technology to drive smarter
healthcare processes and positively impact patient care.
Who We Are:
Iodine is an enterprise AI company that is championing a radical rethink of how to create value for
healthcare professionals, leaders, and their organizations: automating complex clinical tasks, generating
insights and empowering intelligent care. Powered by one of the largest sets of clinical data and use
cases available, our groundbreaking clinical machine-learning engine, Cognitive ML, constantly ingests
the patient record to generate real-time, highly focused, predictive insights that clinicians and hospital
administrators can leverage to dramatically augment the management of care delivery.
What we're looking for:
Iodine thrives on innovation. We are looking for a Senior Data Scientist that will help us discover the
information hidden in vast amounts of data. You will be joining a small team that is tackling many
interesting healthcare problems using ML. Because we work on the cutting edge of a lot of technologies,
we need someone who is a creative problem solver, resourceful in getting things done, and productive
working independently or collaboratively. You will be accessing and shaping our enormous amount of
data to help drive our future innovation.
What you'll Do:
Work with a team of passionate data scientists to further the mission of Iodine and the Data Science
team. Collaborate with teams, including both technical and business teams, from different functional
areas to solve complex problems. Develop statistical and machine learning algorithms, named entity
recognition/named entity linking models, inference rules, probabilistic models, simulation models, and
visualizations for client pilots and scaled solutions. Leverage Natural Language Processing (NLP) tools
and techniques including identification and extraction of named entities and relationships, summarization,
and disambiguation using a variety of clinical document formats. Lead multiple projects in parallel and
assist other team members and conduct directed research and development in natural language
processing and applied machine learning on healthcare datasets.
Present results and overviews to internal and external audiences and serve as a mentor to junior team
members. Consult with business teams to provide guidance and capture feedback as required. Perform
exploratory data analysis (EDA), data profiling, and data cleaning on a variety of datasets. Learn and
identify data relationships across multiple contributing sources, developing and discovering direct and
inferred data relationships where rules can be defined and consistently applied, and other strategies to
optimize the efficiency and quality of the data being collected, normalized, and delivered. Acquire data
from primary or secondary data sources to maintain data quality programs, and leverage these sources to
identify and interpret trends or patterns in complex datasets. Create innovative frameworks and solutions
for extracting value from client data.
What we'd Love to See • 5+ years hands-on experience in machine learning, statistics, NLP• Ability to effectively communicate technical concepts to both technical and non-technical staff members• Self-motivated and self-directed, able to learn new technologies quickly and adapt to a rapidly changing
environment• Proficiency in ML/Data Science languages and tools including Python (and packages including but not
limited to Jupyter notebooks, pandas, numpy, scikit-learn, pytorch) and SQL• Proficiency in using SQL and noSQL databases, including PostgreSQL, ElasticSearch• Proficiency in NLP tools including cTAKES, spaCy, nltk• Master's Degree or PhD strongly preferred in Computer Science, Statistics, Mathematics, Econometrics,
Operations Research, Physics or a related field with a substantial research component and focus on data
analysis• Ability to demonstrate proficiency in machine learning, statistics, data analysis, NLP. Must have an excellent
knowledge of advanced methods, and experience in applying those methods to a variety of problems• Solid grasp of probability, statistical or mathematical modeling with analytical and quantitative problem-
solving ability. Experience with healthcare data is strongly preferred.• Demonstrated experience in applying machine learning to real-world problems• Familiarity with software development cycles, version control systems (including Git), interacting with
RESTful APIs, Mac and Linux platforms• Familiarity with ETL tools and processes• Familiarity with MLOps, model deployment, model monitoring, model versioning• Experience with improving model runtime performance and data query performance• Experience working in an agile team environment. Understanding of code promotion, code turnover to
operations, version control, and QA procedures.• Conduct code walkthroughs, peer reviews, and produce technical documentation
Desired additional experience/skills • Familiarity with big data and distributed/cloud computing technologies such as Apache Airflow, Kafka,
Apache Spark, AWS platform data services• Knowledge of healthcare data space, including clinical data formats and workflows is strongly preferred• Very strong scripting and automation skills - you believe you can automate everything• Understand database platform layouts and configurations• Ability to efficiently balance multiple projects in a rapidly changing environment• Experience in a professional services environment with exposure to senior functional leaders
*Please note this position is not restricted solely to the responsibilities listed above and that the job scope and
responsibilities are subject to change.*