2 hours ago
Remote, United StatesStaff+
Responsibilities
- Architect and develop scalable AI platforms and frameworks supporting healthcare-specific LLM applications, regulatory requirements, and ethical considerations.
- Build AI pipelines processing structured and unstructured healthcare data, including FHIR, HL7, clinical notes, and claims data.
- Develop domain-specific AI architectures for clinical decision-making, revenue cycle management, and patient engagement.
- Design enterprise-grade RAG, hybrid retrieval, vector database, knowledge-graph, model-routing, and multi-agent orchestration systems.
- Implement model evaluation, observability, logging, tracing, fairness, robustness, AI guardrails, prompt-injection defenses, and output validation.
- Partner with engineering to move research prototypes into highly available production environments across cloud and on-premises deployments.
- Serve as the primary technical authority for AI platform development, mentor junior AI designers and engineers, and lead technical knowledge-sharing.
- Ensure compliance with healthcare privacy and data security requirements.
Requirements
- Master's degree in Computer Science, AI, Machine Learning, or a related field and 10+ years of experience developing AI/ML platforms on cloud and on-premises environments.
- Alternatively, 15+ years of software engineering experience in AI, Machine Learning, or a related field with 10+ years of experience building AI/ML platforms.
- Proficiency in Python and modern machine learning libraries, with experience in GenAI, LLMs, transformer architectures, and advanced model routing.
- Hands-on experience with PyTorch, TensorFlow, Hugging Face, LangChain, and LlamaIndex.
- Deep expertise building enterprise RAG systems, including advanced chunking, hybrid search, vector database management, and retrieval optimization.
- Experience with autonomous AI agents, reasoning systems, Agent-to-Agent communication protocols, Model Context Protocol, context management, stateful memory, caching, and long-running agent contexts.
- Experience with LLM and agent observability, specialized tracing, logging, scalable systems, and monitoring reasoning steps, token usage, and latency.
- Strong experience applying AI architectures to scalable enterprise platforms, cloud and on-premises deployments, and MLOps/LLMOps practices.
- Experience with knowledge-graph databases such as Neo4j, NoSQL and SQL databases, native vector databases, GraphRAG, and hybrid retrieval architectures.
- Experience with Kubernetes, Terraform, multi-agent orchestration frameworks, LLM evaluation frameworks, fine-tuning techniques such as LoRA and PEFT, model distillation, and platform-wide AI guardrails is preferred.
- Ability to take complex, non-deterministic LLM and multi-agent architectures from concept through production-grade deployment.
Benefits
- Remote role in the United States with up to 10% domestic travel.
- Relocation assistance is not authorized.
- New hires starting October 1, 2025 or later must attend on-site onboarding at a designated company location, with travel coordinated and paid by the company.
- Benefits may include medical, dental and vision coverage, health savings accounts, flexible spending accounts, disability benefits, life insurance, paid absences, retirement benefits, and voluntary benefits.