Clinical AI LLM Engineer & RAG Architect

Mount Sinai Health System; United States; On-site; USD 110,000 - 165,000; Full time

Job summary

Mount Sinai Health System seeks an LLM Engineer I to design, build, and deploy LLM-powered applications, including clinical chatbots and copilots, across the SinAI Assurance Lab.

You will develop RAG pipelines, integrate vector databases with EHR data, and implement scalable data validation and monitoring to ensure patient safety and compliance. Collaboration with AI product teams and governance bodies is essential.

Qualifications

• Bachelor's degree in a quantitative field (CS, stats, math)
• Proficiency in Python, SQL, and at least one programming language
• Experience with big data technologies (Hadoop, Spark) and data engineering
• Familiarity with ML/Ops tools (MLflow, Kubeflow, Airflow)
• Experience deploying and monitoring AI/ML systems in production
• Understanding of RAG architectures and LLM-based apps
• Hands-on with LangChain, LlamaIndex, or similar frameworks
• Knowledge of HIPAA or healthcare data practices is a plus

Responsibilities

• Design, build, and deploy LLM-powered applications including clinical chatbots and copilots
• Develop RAG pipelines integrating vector databases with EHR data and documents
• Create scalable data pipelines for model validation and monitoring
• Ensure compliance, performance, and patient safety across ML systems
• Collaborate with AI product teams, clinical stakeholders, and governance bodies

Skills

Python

SQL

Big data

Docker

Kubernetes

LangChain

LlamaIndex

RAG

Model deployment

Monitoring

Education

Bachelor's degree in Computer Science / Statistics / Mathematics or related

Tools

MLflow

Kubeflow

Airflow

Pinecone/Weaviate/FAISS

Job description

Mount Sinai Health System seeks an LLM Engineer I to design, build, and deploy LLM-powered applications, including clinical chatbots and copilots, across the SinAI Assurance Lab.

You will develop RAG pipelines, integrate vector databases with EHR data, and implement scalable data validation and monitoring to ensure patient safety and compliance. Collaboration with AI product teams and governance bodies is essential.