Abby Care
Applied AI Engineer
San Francisco (Remote)$175k–$235kfulltimemidAdded yesterday
About this role
Abby Care seeks an Applied AI Engineer to build AI-powered products and workflow automation for their home care platform. You'll develop production systems that help caregivers, clinicians, and operational teams deliver better care by working on clinical document processing, intake automation, and intelligent workflows.
What you'll do
- Build AI agents, copilots, and intelligent workflows for caregivers and operational teams
- Develop backend services, APIs, and data pipelines to move AI solutions from prototype to production
- Create systems that extract, retrieve, and reason over clinical documents and healthcare data
- Build datasets, measure performance, and improve models based on production feedback
- Partner with Product, Design, Clinical, and Operations teams to understand workflows and identify edge cases
- Write maintainable, tested code and contribute to shared AI infrastructure and evaluation frameworks
What they're looking for
- Large language models and AI application development
- Python backend development and API design
- Data pipeline and ETL work
- Healthcare domain knowledge or ability to learn clinical workflows
- Machine learning evaluation and monitoring
- Prompt engineering and retrieval-augmented generation
- Software testing and production system reliability
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Abby Care
Abby Care builds AI-powered products designed to support family caregivers in delivering quality home care. The company is hiring Full-Stack Engineers to own features end-to-end, working with modern cloud and AI technologies across clinical and operational teams.
View all jobs at Abby CareLikely interview questions
- Describe your experience taking an AI prototype into production—what obstacles did you encounter and how did you overcome them?
- How have you approached building evaluations and metrics for AI systems, especially in domains where correctness is critical?