onsite
AI Engineer - WelbeHealth
AI Engineer
AI Engineer building and deploying AI-powered healthcare solutions using enterprise models, RAG pipelines, and agentic workflows on AWS, focused on improving care for seniors in a PACE program.
About the role
Key Responsibilities
- Design, develop, and maintain AI-powered applications that support senior care, including participant context engines and retrieval‑augmented generation pipelines.
- Integrate and orchestrate enterprise AI models within production environments, ensuring scalability and reliability on AWS.
- Collaborate with data scientists, clinicians, and product teams to translate healthcare challenges into technical solutions.
- Implement agentic workflows that automate decision support and enhance user experience for care coordinators.
- Monitor model performance, conduct A/B testing, and iterate on solutions based on real‑world feedback.
Requirements
- Proficiency in Python and experience building production‑grade ML pipelines.
- Strong understanding of NLP techniques, especially Retrieval‑Augmented Generation and related architectures.
- Hands‑on experience deploying models on AWS (SageMaker, Lambda, ECS/EKS).
- Excellent problem‑solving skills and ability to work cross‑functionally in a fast‑moving environment.
- Passion for leveraging technology to improve healthcare outcomes for vulnerable populations.
Skills
pythonmachine learningawsnlp