Description

Build interoperable, context-aware AI agents for clinical and administrative platforms.

This role is hybrid.

Responsibilities

• Design and implement Agent-to-Agent (A2A) protocols for autonomous collaboration and task delegation.
• Architect Model Context Protocol (MCP) pipelines to ensure persistent, memory-augmented LLM interactions.
• Build multi-agent systems orchestrated by LLM-driven planning modules for benefit processing and clinical summarization.
• Fine-tune domain-specific LLMs and NLP models for document understanding and intent classification.
• Develop retrieval-augmented generation (RAG) systems using structured FHIR/ICD-10 and unstructured data sources.

Required Skills

• 7+ years of experience in applied AI focusing on LLMs, transformers, agent frameworks, or NLP.
• Hands-on experience with Agent-to-Agent protocols, LangGraph, AutoGen, CrewAI, or similar orchestration tools.
• Implementation experience with Model Context Protocols (MCP) for modular agent interactions.
• Proficiency in Python and ML/NLP libraries including Hugging Face Transformers, PyTorch, LangChain, and spaCy.
• Knowledge of healthcare data standards such as FHIR, HL7, ICD/CPT, and X12 EDI formats.
• Experience with cloud-native development on AWS, Azure, or GCP, including Kubernetes, Docker, and CI/CD.
• Master’s or Ph.D. in Computer Science, Machine Learning, Computational Linguistics, or a related field.

Preferred Skills

• Deep understanding of MCP and VectorDB integration for dynamic agent memory.
• Prior work on LLM-based agents in production systems or large-scale healthcare operations.

Key Skills

Education

Any Graduate