Compunnel
Job Summary
We are hiring a Senior Data Scientist with deep expertise in AI agent architectures, large language models (LLMs), natural language processing (NLP), and hands-on experience with Agent-to-Agent (A2A) Protocols and Model Context Protocols (MCP).
This role is critical in building interoperable, context-aware, and self-improving agents that operate across clinical, administrative, and benefits platforms in healthcare.
Key Responsibilities Design and implement A2A protocols for autonomous collaboration and task delegation between specialized AI agents (e.g., ClaimsAgent, EligibilityAgent, ProviderMatchAgent). Architect and operationalize MCP pipelines to enable persistent, memory-augmented, and contextually grounded LLM interactions. Build intelligent multi-agent systems orchestrated by LLM-driven planning modules for benefit processing, prior authorization, clinical summarization, and member engagement. Fine-tune and integrate domain-specific LLMs and NLP models (e.g., medical BERT, BioGPT) for document understanding, intent classification, and personalized recommendations. Develop retrieval-augmented generation (RAG) systems and structured context libraries for dynamic knowledge grounding across structured (FHIR/ICD-10) and unstructured sources (EHR notes, chat logs). Collaborate with engineering and data architecture teams to build scalable, secure, and compliant agentic pipelines. Lead research and prototyping in memory-based agent systems, RLHF, and context-aware task planning. Contribute to production deployment through robust MLOps pipelines for model versioning, monitoring, and continuous improvement. Required Qualifications
Master’s or Ph.D. in Computer Science, Machine Learning, Computational Linguistics, or a related field. 7+ years of experience in applied AI with a focus on LLMs, transformers, agent frameworks, or NLP in healthcare. Hands-on experience with A2A protocols and multi-agent orchestration tools (e.g., LangGraph, AutoGen, CrewAI). Practical experience implementing MCP for long-lived conversational memory and modular agent interactions. Strong coding skills in Python and proficiency with ML/NLP libraries (e.g., Hugging Face Transformers, PyTorch, LangChain, spaCy). Familiarity with healthcare benefit systems, claims data, and eligibility rules. Experience with healthcare data standards (FHIR, HL7, ICD/CPT, X12 EDI). Cloud-native development experience on AWS, Azure, or GCP, including Kubernetes, Docker, and CI/CD. Preferred Qualifications
Expertise in MCP + VectorDB integration for dynamic agent memory and retrieval. Experience deploying LLM-based agents in production healthcare systems. Exposure to voice AI, automated care navigation, or AI triage tools. Published research or patents in agent systems, LLM architectures, or contextual AI frameworks.
Education:
Bachelors Degree, Doctoral Degree, Masters Degree
We are hiring a Senior Data Scientist with deep expertise in AI agent architectures, large language models (LLMs), natural language processing (NLP), and hands-on experience with Agent-to-Agent (A2A) Protocols and Model Context Protocols (MCP).
This role is critical in building interoperable, context-aware, and self-improving agents that operate across clinical, administrative, and benefits platforms in healthcare.
Key Responsibilities Design and implement A2A protocols for autonomous collaboration and task delegation between specialized AI agents (e.g., ClaimsAgent, EligibilityAgent, ProviderMatchAgent). Architect and operationalize MCP pipelines to enable persistent, memory-augmented, and contextually grounded LLM interactions. Build intelligent multi-agent systems orchestrated by LLM-driven planning modules for benefit processing, prior authorization, clinical summarization, and member engagement. Fine-tune and integrate domain-specific LLMs and NLP models (e.g., medical BERT, BioGPT) for document understanding, intent classification, and personalized recommendations. Develop retrieval-augmented generation (RAG) systems and structured context libraries for dynamic knowledge grounding across structured (FHIR/ICD-10) and unstructured sources (EHR notes, chat logs). Collaborate with engineering and data architecture teams to build scalable, secure, and compliant agentic pipelines. Lead research and prototyping in memory-based agent systems, RLHF, and context-aware task planning. Contribute to production deployment through robust MLOps pipelines for model versioning, monitoring, and continuous improvement. Required Qualifications
Master’s or Ph.D. in Computer Science, Machine Learning, Computational Linguistics, or a related field. 7+ years of experience in applied AI with a focus on LLMs, transformers, agent frameworks, or NLP in healthcare. Hands-on experience with A2A protocols and multi-agent orchestration tools (e.g., LangGraph, AutoGen, CrewAI). Practical experience implementing MCP for long-lived conversational memory and modular agent interactions. Strong coding skills in Python and proficiency with ML/NLP libraries (e.g., Hugging Face Transformers, PyTorch, LangChain, spaCy). Familiarity with healthcare benefit systems, claims data, and eligibility rules. Experience with healthcare data standards (FHIR, HL7, ICD/CPT, X12 EDI). Cloud-native development experience on AWS, Azure, or GCP, including Kubernetes, Docker, and CI/CD. Preferred Qualifications
Expertise in MCP + VectorDB integration for dynamic agent memory and retrieval. Experience deploying LLM-based agents in production healthcare systems. Exposure to voice AI, automated care navigation, or AI triage tools. Published research or patents in agent systems, LLM architectures, or contextual AI frameworks.
Education:
Bachelors Degree, Doctoral Degree, Masters Degree