Senior Data Scientist

About the Role

We are changing the way healthcare uses data. About 80% of healthcare data is under-utilized because it is too messy or unstructured to analyze. The healthcare industry needs technology solutions that can process this data and extract insights. This is the challenge that Apixio addresses.

Apixio augments the ability to decipher and understand patient information. This translates into better care delivery, lower costs, and streamlined processes. We process millions of patients every year and we’re growing not only in the number of patients but also the kind of data we analyze. Come help us improve healthcare with technology!

We are looking for a motivated Senior Data Scientist as a Generalist to help us extract insights from the vast amounts of structured and unstructured healthcare data. In this critical role, you will develop novel models and algorithms to solve a wide range of problems in the healthcare industry. This includes improving our industry-leading risk adjustment models as well as exploring new product offerings for emerging market segments. The right candidate will have the opportunity to increase efficiency in the healthcare system, assist providers to deliver better care, and positively impact the lives of millions of patients.

Qualifications

• Advanced degree in computer science, data science, statistics, or a related quantitative field, or equivalent work experience.
• 4+ years of hands-on experience in data science and machine learning, preferably in an industry setting
• 4+ years of working experience in Python
• Experience in using data analysis toolkits such as NumPy, Pandas, SQL, etc.
• Strong background in statistical methods for supervised and unsupervised machine learning, especially time series classification, clustering, dimensionality reduction, outlier detection and classification approaches in high-cardinality spaces
• Experience in deep learning frameworks like PyTorch or TensorFlow
• Working experience in designing and building natural language processing (NLP) models for tasks like text classification, named-entity recognition, and dependency parsing
• Demonstrable ability to translate business requirements into effective machine learning solutions, while navigating ambiguity

Bonus Experience (not required, but useful at Apixio; in order of importance)

• Familiarity with healthcare data ontologies and code systems (e.g. ICD, CPT, SNOMED)
• Background in experiment design, sampling, model/data drift detection, and A/B testing
• Experience developing predictive models for structured healthcare datasets, and/or graph-based data
• Expertise in working with large, distributed datasets and designing scalable data processing pipelines (e.g. Spark, Databricks, MLFlow)
• Practical experience in projects using deep learning time series libraries, such as Prophet
• Understanding of the healthcare industry and the challenges it faces

Responsibilities

• Lead the development of advanced machine learning and NLP models to extract insights from structured and unstructured healthcare data
• Perform data cleaning, feature engineering, and model optimization to continuously improve model performance
• Collaborate cross-functionally with product managers, engineers, and domain experts to define key metrics and translate business requirements into technical solutions
• Implement systems for long-term model improvement and data quality enhancement (e.g. active learning, continuous learning)
• Stay up-to-date with the latest research and industry trends, and apply innovative techniques to solve complex healthcare problems

After 3 Months, You Will…

• have a strong grasp of the underlying technologies and be fully integrated into the ongoing model development efforts.

After 1 Year, You Will…

• be an independent researcher, developing models for new and existing products. You will own the models internally, communicating with stakeholders to ensure the model and product succeed. You will become a subject matter expert, providing guidance and recommendations to other teams.