Principal Machine Learning Architect / Engineer + Data Scientist
Aetion
·
Posted:
April 19, 2023
·
Hybrid
About the position
The Principal Machine Learning Architect / Engineer + Data Scientist will be responsible for defining, implementing, and integrating innovative, robust, and reusable ML pipelines into the Aetion technology platform. This role requires a highly analytical, problem-solving mindset with a demonstrated ability for conducting statistical and machine learning research. The successful candidate will work alongside engineering, science, and product teams to identify and solve high-value machine learning use-cases, using a variety of machine learning methods to solve healthcare-related problems using cloud-based technologies. They will also evangelize new ML tools and their benefits with both internal and client-facing teams, and research topics in machine learning and statistics to stay up-to-date on emerging trends in the field.
Responsibilities
- Work alongside engineering, science, and product to identify and solve high-value machine learning use-cases.
- Use a variety of machine learning methods to solve healthcare-related problems using cloud-based technologies.
- Design and implement robust, re-usable data/ML pipelines using open-source technology such as Python, Spark, and R. Drive the validation and transparency of these ML models.
- Evangelize new ML tools and their benefits with both our internal and client-facing teams; engage with our clients to understand their needs, and how Aetion’s ML tools can meet these needs.
- Research topics in machine learning and statistics to stay up-to-date on emerging trends in the field.
Requirements
- A BSc/MSc/PhD degree (or equivalent) in mathematics, statistics, computer science, electrical engineering, or a related STEM field.
- 8+ years of relevant work experience.
- Highly analytical, problem-solving mindset with a demonstrated ability for conducting statistical and machine learning research (in the form of a thesis, publications, or side projects) and independently solving ill-defined problems on data from heterogeneous sources.
- Expert in Python and/or R programming for full data science lifecycle (ETL / database connection, data exploration and visualization, cleaning/pre-processing, feature engineering, classification and regression, model evaluation, deployment / monitoring). Example of libraries: Tensorflow/Keras, Pytorch / Scikit-learn.
- Proven ability to partner with product teams to define workflows that meet client needs.
- Demonstrated excellence in written and verbal communication, in fluent English, with ability to explain complex analyses to a variety of audiences.
- Detail-oriented with a demonstrated ability to work under time pressure and balance multiple competing / changing priorities.
- Experience working with large, complex medical / healthcare data (e.g., insurance claims, EHR, CDISC)
- Experience with version control software (e.g., Git)
- Experience with big data workloads (e.g., Spark, Databricks)
- Experience working within cloud-centric systems (AWS)
- Experience working with containerized compute (e.g., Docker)
- Experience working with relational databases
- Knowledge of software engineering best practices
- Experience in the healthcare industry