Senior Data Scientist, Healthcare

Responsibilities will include:

• Act as data science champion across all functions at AH, working to understand the primary business objectives across these functions and applying your DS acumen to solve for them.
• Serve as a highly-collaborative thought partner across product, engineering, and clinical operations on all things data.
• Demonstrate excellence in your understanding of the healthcare domain and related data assets (i.e., claims, EHR data, clinical notes, and imaging), as well as ML/AI applications.
• Develop and maintain scalable data/feature engineering pipelines using tools such as SQL, Spark, Python, and Feature Stores.
• Identify, implement, and maintain appropriate ML & AI techniques for a wide variety of healthcare-related business use cases. These will include but not be limited to predicting healthcare utilization, clinical segmentation, sentiment analysis, and applications of NLP/LLMs to drive business value.
• Deploy optimal models to production, using model versioning and registries in AWS SageMaker.
• Develop and maintain a system for continuous, automated feedback and optimization across model deployments. This will include model experimentation, as well as continuous monitoring for model/data drift and performance.
• Work within the DS team to contribute to process improvement and best practices which drive transparency, reproducibility, and scalability of DS-related activities.
• Commit to a culture of continuous growth by keeping abreast of state-of-the-art methods, participating in regular DS working sessions, and mentoring others.

What makes you a fit for the team:

• You approach your work with humility and flexibility, recognizing that our system of care will need to learn and adapt to the needs of patients with complex needs
• You show empathy for the needs of patients, clinicians, and your colleagues to change the fundamental paradigm of care delivery for marginalized patients
• You have a distinctive ability to get a highly cross-functional group of stakeholders – technical and non-technical – on the same page
• Your curiosity drives you to be an expert of your data and analytic products and you strive to elevate your peers and the company as a learning organization
• You focus on getting things done in the most effective, efficient manner for the task at hand – rather than following a specific process for its own sake
• You have the resilience to dive headfirst into challenging problems – healthcare is complicated and there’s a lot to be fixed
• You are excited to work in a startup environment, with the ambiguity and shifting priorities that might come with it at times

Desired skills and experience:

• Required:
• 3-5 years experience in health data science, ML, & AI
• Strong command of multiple areas of data science/ML, including statistics, causal inference, supervised and unsupervised machine learning algorithms, common LLMs (OpenAI, Claude 3, Llama 3), and essentials of prompt engineering.
• Strong command of Python and standard packages for data science/ML, including Tensorflow or PyTorch
• Strong command of data processing tools and technology for production-grade ML workflows (e.g., SageMaker Pipelines & Docker)
• Strong analytical and problem solving skills, with the ability to efficiently harmonize disparate data, conduct complex analyses, and present findings fluently.
• Excellent written and verbal communication skills
• Highly inquisitive, self-motivated, self-directed and attentive to detail
• Preferred:
• Familiarity with software development life cycle and project management tools (such as Agile and JIRA)
• Familiarity with value-based care, quality metrics, and clinical terminologies
• Familiarity with AWS cloud infrastructure