remote
Tech - Staff AI Engineer, Agent Platform
AI Engineer
Lead the design and scaling of a medical AI agent platform, leveraging Python, ML, NLP, and cloud infrastructure to automate charting, coding, and care coordination for thousands of providers.
About the role
Key Responsibilities
- Architect and develop end‑to‑end AI agent pipelines that automate charting, coding, and care gap closure for a large, multi‑specialty user base.
- Collaborate with data scientists to refine NLP models, ensuring high accuracy and compliance with medical regulations.
- Design scalable, containerized services on AWS, using Docker and Kubernetes to support real‑time inference and batch processing.
- Implement robust monitoring, logging, and A/B testing frameworks to continuously improve agent performance.
- Mentor junior engineers, conduct code reviews, and drive best practices in CI/CD and cloud security.
Requirements
- 5+ years of production software engineering experience, with a focus on AI/ML systems.
- Strong proficiency in Python, deep learning frameworks (PyTorch/TensorFlow), and NLP libraries.
- Hands‑on experience deploying containerized workloads on AWS (ECS/EKS, Lambda, S3, SageMaker).
- Solid understanding of data pipelines, version control, and automated testing.
- Excellent communication skills and a collaborative mindset.
Skills
pythonmachine learningnlpawsdockerkubernetes