Remote Anywhere in U.S.
Ciitizen is now Invitae
Bringing together the power of genomic and clinical information within a new kind of patient data platform to improve
healthcare decision making at personal and systemwide levels. Learn more here.
About this role:
This pivotal role sits at the intersection of data science, clinical informatics, and product. As the Product Manager, Data Science, your mandate is to identify areas in our clinical document processing process and pipeline where we can leverage data driven approaches, specifically data science, to maximize the throughput of our clinical data production pipeline as well as the quality and semantic richness of the data it produces. One of your key responsibilities will be to develop and manage a Data Science roadmap. You will work with the data science and engineering teams to develop production quality ML/DL pipelines, as well as develop strong cross-functional relationships with key stakeholders across Product and Clinical Operations. You’ll maximize the ability of Data Science and Clinical Informatics to be a force multiplier for the organization.
As a part of this role, you will be responsible to identify data sources from within the Ciitizen Data processing pipeline, create datasets for model training, develop a labeling and annotation strategy (including selection of tools and service providers), creating the ground truth, feature engineering and algorithm selection. You will also work with the data science and engineering team to setup an infrastructure for end to end metrics capture and analysis of how the ML/DL models are performing as units as well as end to end. Finally, you will report the ML/DL pipeline performance in terms of business outcomes (quality, performance, scale) to the key stakeholders.
This is a senior position, reporting to our technical cofounder and VP of engineering.
Key deliverables and responsibilities for this role would include, but are not limited to:
- Working with the clinical science, clinical operations and clinical informatics teams to develop a detailed understanding of the data workflows
- Identify and prioritize the areas that can get the biggest impact from using data science techniques
- Create a prioritized roadmap of ML/DL projects and define a clear and measurable success criteria for them
- Recommend the optimal ML/DL approach and technical design in collaboration with the Data Science and Engineering teams
- Productize the ML/DL pipelines and ensure that their performance and quality meets a high bar, and is measurable using business metrics
- Create a Data Science and Engineering dashboard that gives the stakeholders real time visibility on the key performance and quality metrics as they impact the business
- Drive towards a more agile pipeline development cycle (ideally 2-4 weeks).
- Manage external partners or contractors for labeling and annotation work
- BS or higher in computer science, statistics or data science
- Hands on experience with working on data platforms and data driven decision making applications
- Deep knowledge of data operations and processes
- Deep expertise in all data science methodologies, techniques and approaches
- Hands on experience with Computer Vision and NLP based pipelines
- Experience with dataset curation, labeling, annotation tools and strategies
- Hands on expertise with defining data quality parameters and measurement techniques
- Hands on experience with data analytics tools and practices
- Expertise with healthcare data is highly desirable
- Hands on experience in working with clinical operations, data scientists, and bioinformatics teams to deliver a unified data model/dictionary
- Experience working with external partners in areas such as labeling, annotation etc.
- At least 8 years of relevant experience
At Invitae, we value diversity and provide equal employment opportunities (EEO) to all employees and applicants without regard to race, color, religion, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status. We will consider for employment qualified applicants with criminal histories in a manner consistent with the requirements of the San Francisco Fair Chance Ordinance.