Overview:
This role focuses on deploying AI-powered solutions to extract structured data from unstructured medical charts. The AI Engineer will work with technical and clinical teams to bring AI models into real-world use, improving efficiency in healthcare data processing while ensuring accuracy, usability and responsible AI practices.
Responsibilities:
- Develop, test, and deploy LLM-powered extraction pipelines for clinical text at scale.
- Automate prompt execution, result validation, and error handling to enhance reliability.
- Monitor and maintain production AI models, ensuring uptime, accuracy, and compliance.
- Work with product, data, engineering, and clinical teams to integrate AI outputs into real-world solutions.
- Evaluate and integrate third-party AI solutions when appropriate.
- Stay current with advancements in LLM deployment, model serving, and responsible AI practices.
- As a growth organization, roles and responsibilities often evolve and adapt over time. As such, this job description may not comprehensively account for future activities, responsibilities, and priorities—these may evolve right along with us!
Qualifications:
Required Abilities, Education, and Skills:
- 5+ years of experience in AI deployment or applied Machine Learning.
- Strong software engineering foundation with proficiency in Python.
- Familiarity with cloud platforms, data engineering and pipeline automation.
- Bachelor’s degree in Computer Science, AI, a related field, or equivalent work experience.
- Strong cross-functional collaboration skills.
- Proven track record of thriving in a start-up environment.
Preferred Abilities, Education and Skills:
- Experience deploying LLMs in production environments.
- Advanced degree in Computer Science or related field.
- Experience integrating AI with healthcare data (EHRs, clinical databases).
- Experience working in regulated industries with an understanding of security, compliance, and responsible AI.