Compunnel, Inc.
We are hiring a Senior Data Scientist with deep expertise in AI agent architectures, large language models (LLMs), and natural language processing (NLP).
This role is critical in developing interoperable, context-aware, and self-improving agents that operate across clinical, administrative, and benefits platforms in the healthcare domain.
Key Responsibilities
Design and implement Agent-to-Agent (A2A) protocols for autonomous collaboration, negotiation, and task delegation between specialized AI agents (e.g., ClaimsAgent, EligibilityAgent, ProviderMatchAgent). Architect and operationalize Model Context Protocol (MCP) pipelines to support 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 using structured (FHIR/ICD-10) and unstructured sources (EHR notes, chat logs). Collaborate with engineers and data architects to build scalable, secure, and explainable agentic pipelines compliant with healthcare regulations (HIPAA, CMS, NCQA). Lead research and prototyping in memory-based agent systems, reinforcement learning with human feedback (RLHF), and context-aware task planning. Contribute to production deployment through robust MLOps pipelines for versioning, monitoring, and continuous model 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 Agent-to‑Agent protocols and multi‑agent orchestration tools (e.g., LangGraph, AutoGen, CrewAI). Practical experience implementing Model Context Protocols (MCP) for modular agent interactions and conversational memory. Strong coding skills in Python and proficiency with ML/NLP libraries such as Hugging Face Transformers, PyTorch, LangChain, spaCy. Familiarity with healthcare benefit systems, including plan structures, 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
Deep understanding of MCP and VectorDB integration for dynamic agent memory and retrieval. Prior experience deploying LLM‑based agents in production or large‑scale healthcare operations. Experience with voice AI, automated care navigation, or AI triage tools. Published research or patents in agent systems, LLM architectures, or contextual AI frameworks.
#J-18808-Ljbffr
Design and implement Agent-to-Agent (A2A) protocols for autonomous collaboration, negotiation, and task delegation between specialized AI agents (e.g., ClaimsAgent, EligibilityAgent, ProviderMatchAgent). Architect and operationalize Model Context Protocol (MCP) pipelines to support 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 using structured (FHIR/ICD-10) and unstructured sources (EHR notes, chat logs). Collaborate with engineers and data architects to build scalable, secure, and explainable agentic pipelines compliant with healthcare regulations (HIPAA, CMS, NCQA). Lead research and prototyping in memory-based agent systems, reinforcement learning with human feedback (RLHF), and context-aware task planning. Contribute to production deployment through robust MLOps pipelines for versioning, monitoring, and continuous model 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 Agent-to‑Agent protocols and multi‑agent orchestration tools (e.g., LangGraph, AutoGen, CrewAI). Practical experience implementing Model Context Protocols (MCP) for modular agent interactions and conversational memory. Strong coding skills in Python and proficiency with ML/NLP libraries such as Hugging Face Transformers, PyTorch, LangChain, spaCy. Familiarity with healthcare benefit systems, including plan structures, 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
Deep understanding of MCP and VectorDB integration for dynamic agent memory and retrieval. Prior experience deploying LLM‑based agents in production or large‑scale healthcare operations. Experience with voice AI, automated care navigation, or AI triage tools. Published research or patents in agent systems, LLM architectures, or contextual AI frameworks.
#J-18808-Ljbffr