Cynet systems Inc
Job Description
Pay Range: $70hr - $75hr
The AI/ML Engineer – Multi-Agent Systems is responsible for designing, implementing, and operationalizing autonomous multi-agent AI systems in healthcare.
This role involves developing Agent-to-Agent (A2A) protocols, Model Context Protocol (MCP) pipelines, retrieval-augmented generation (RAG) systems, and integrating domain-specific LLMs and NLP models to streamline benefit processing, prior authorization, clinical summarization, and member engagement.
The engineer will collaborate with data architects and engineers to ensure secure, explainable, and compliant AI solutions while contributing to production deployment through robust MLOps pipelines.
Requirements
Design and implement Agent-to-Agent (A2A) protocols for autonomous collaboration, negotiation, and task delegation between specialized AI agents.
Architect and operationalize Model Context Protocol (MCP) pipelines for persistent, memory-augmented, and contextually grounded LLM interactions.
Build intelligent multi-agent systems orchestrated by LLM-driven planning modules for healthcare workflows.
Fine-tune and integrate domain-specific LLMs and NLP models for document understanding, intent classification, and personalized plan recommendations.
Develop retrieval-augmented generation (RAG) systems and structured context libraries to enable knowledge grounding across structured (FHIR/ICD-10) and unstructured sources (EHR notes, chat logs).
Collaborate with engineers and data architects to build scalable, secure, explainable, and compliant agentic pipelines.
Lead research and prototyping in memory-based agent systems, reinforcement learning with human feedback (RLHF), and context-aware task planning.
Contribute to production deployment via MLOps pipelines for model versioning, monitoring, and continuous improvement.
Experience
7+ years of applied AI experience focusing on LLMs, transformers, agent frameworks, or NLP in healthcare.
Hands-on experience with Agent-to-Agent protocols, LangGraph, AutoGen, CrewAI, or similar multi-agent orchestration tools.
Practical experience with Model Context Protocols (MCP) for long-lived conversational memory and modular agent interactions.
Strong coding experience in Python with proficiency in 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 such as FHIR, HL7, ICD/CPT, and X12 EDI formats.
Cloud-native development experience on AWS, Azure, or GCP, including Kubernetes, Docker, and CI/CD pipelines.
Responsibilities
Design, implement, and maintain multi-agent AI systems for healthcare applications.
Fine-tune and deploy domain-specific LLMs and NLP models for clinical and benefits processing.
Develop MCP pipelines and retrieval-augmented generation systems for contextually grounded interactions.
Collaborate with cross-functional teams to ensure secure, compliant, and scalable AI solutions.
Lead research and prototyping efforts for advanced AI agent systems and RLHF implementations.
Contribute to MLOps pipelines for production deployment, monitoring, and continuous model improvement.
Skills
Agent-to-Agent protocol design and multi-agent orchestration tools.
Model Context Protocol (MCP) design and implementation.
Python programming and ML/NLP library expertise.
Retrieval-augmented generation (RAG) system development.
Healthcare data standards and benefit systems knowledge.
Cloud-native development and containerization (AWS, Azure, GCP, Kubernetes, Docker).
Strong research and problem-solving skills for advanced AI solutions.
Qualifications And Education
Master’s or Ph.D. in Computer Science, Machine Learning, Computational Linguistics, or a related field.
Experience with LLM-based agents in production systems or large-scale healthcare operations is preferred.
Familiarity with voice AI, automated care navigation, or AI triage tools is a plus.
Published research or patents in agent systems, LLM architectures, or contextual AI frameworks is a plus.
#J-18808-Ljbffr
The AI/ML Engineer – Multi-Agent Systems is responsible for designing, implementing, and operationalizing autonomous multi-agent AI systems in healthcare.
This role involves developing Agent-to-Agent (A2A) protocols, Model Context Protocol (MCP) pipelines, retrieval-augmented generation (RAG) systems, and integrating domain-specific LLMs and NLP models to streamline benefit processing, prior authorization, clinical summarization, and member engagement.
The engineer will collaborate with data architects and engineers to ensure secure, explainable, and compliant AI solutions while contributing to production deployment through robust MLOps pipelines.
Requirements
Design and implement Agent-to-Agent (A2A) protocols for autonomous collaboration, negotiation, and task delegation between specialized AI agents.
Architect and operationalize Model Context Protocol (MCP) pipelines for persistent, memory-augmented, and contextually grounded LLM interactions.
Build intelligent multi-agent systems orchestrated by LLM-driven planning modules for healthcare workflows.
Fine-tune and integrate domain-specific LLMs and NLP models for document understanding, intent classification, and personalized plan recommendations.
Develop retrieval-augmented generation (RAG) systems and structured context libraries to enable knowledge grounding across structured (FHIR/ICD-10) and unstructured sources (EHR notes, chat logs).
Collaborate with engineers and data architects to build scalable, secure, explainable, and compliant agentic pipelines.
Lead research and prototyping in memory-based agent systems, reinforcement learning with human feedback (RLHF), and context-aware task planning.
Contribute to production deployment via MLOps pipelines for model versioning, monitoring, and continuous improvement.
Experience
7+ years of applied AI experience focusing on LLMs, transformers, agent frameworks, or NLP in healthcare.
Hands-on experience with Agent-to-Agent protocols, LangGraph, AutoGen, CrewAI, or similar multi-agent orchestration tools.
Practical experience with Model Context Protocols (MCP) for long-lived conversational memory and modular agent interactions.
Strong coding experience in Python with proficiency in 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 such as FHIR, HL7, ICD/CPT, and X12 EDI formats.
Cloud-native development experience on AWS, Azure, or GCP, including Kubernetes, Docker, and CI/CD pipelines.
Responsibilities
Design, implement, and maintain multi-agent AI systems for healthcare applications.
Fine-tune and deploy domain-specific LLMs and NLP models for clinical and benefits processing.
Develop MCP pipelines and retrieval-augmented generation systems for contextually grounded interactions.
Collaborate with cross-functional teams to ensure secure, compliant, and scalable AI solutions.
Lead research and prototyping efforts for advanced AI agent systems and RLHF implementations.
Contribute to MLOps pipelines for production deployment, monitoring, and continuous model improvement.
Skills
Agent-to-Agent protocol design and multi-agent orchestration tools.
Model Context Protocol (MCP) design and implementation.
Python programming and ML/NLP library expertise.
Retrieval-augmented generation (RAG) system development.
Healthcare data standards and benefit systems knowledge.
Cloud-native development and containerization (AWS, Azure, GCP, Kubernetes, Docker).
Strong research and problem-solving skills for advanced AI solutions.
Qualifications And Education
Master’s or Ph.D. in Computer Science, Machine Learning, Computational Linguistics, or a related field.
Experience with LLM-based agents in production systems or large-scale healthcare operations is preferred.
Familiarity with voice AI, automated care navigation, or AI triage tools is a plus.
Published research or patents in agent systems, LLM architectures, or contextual AI frameworks is a plus.
#J-18808-Ljbffr