CTO-Level — Senior LLM Engineer

N1 Healthcare is pioneering a new frontier in precision medicine by harnessing the power of large language models (LLMs), medical natural language processing (NLP), and advanced diagnostics. We deliver AI-generated health intelligence that transforms patient care—at scale, with clinical rigor, and with full personalization. We’re looking for a Chief Technology Officer/Senior LLM Engineer - someone who can build multi-agent LangChain RAG systems while also leading and scaling our entire technology organization. We are also looking for a very senior-level LLM Engineer.

About the roles:

Technology Strategy & Leadership

• Own the entire tech roadmap, spanning AI, cloud infrastructure, DevOps, security, and interoperability.
• Lead, grow, and mentor high-performing engineering teams across AI/ML, backend, and infrastructure.
• Work cross-functionally with clinical, operations, and product leaders to ensure our AI systems are scalable, secure, and medically accurate.
• Cultivate an engineering culture grounded in rigor, innovation, and speed.

Hands-On LLM Engineering

• Design and build production-grade, multi-agent systems using LangChain to automate the synthesis of clinical data, lab results, and genomic information into real-time, personalized health reports.
• Build and optimize retrieval-augmented generation (RAG) pipelines using vector databases such as Weaviate, Pinecone, or Chroma.
• Architect agent-to-agent communication flows, memory persistence strategies, and modular pipelines that support specialized agents (e.g., lab interpreters, genome analysts, longitudinal data aggregators).
• Develop and deploy custom tools, wrappers, and integrations on top of LangChain and leading LLM frameworks.

AI Architecture & Cloud Infrastructure

• Oversee the development and deployment of secure, scalable AI pipelines using LLMs including GPT-4, Claude, and LLaMA2.
• Integrate domain-specific models (e.g., PubMedBERT, Med-PaLM, BioBERT) for enhanced medical understanding and contextualization.
• Manage cloud environments pipelines, and container orchestration (Docker, Kubernetes).
• Design APIs and data ingestion systems that interoperate with EHRs, genomic platforms, and real-time patient data feeds.

Ideal Candidate:

• You’ve developed at least 2 - 3 LangChain multi-agent systems end-to-end—not just reviewed code or led a team.
• 8+ years of engineering experience, including 2+ years of LangChain development.
• Deep expertise in LLM ecosystems, vector search (Weaviate, Pinecone, Milvus), memory persistence (ChromaDB, Redis), and orchestrating agent workflows.
• Proficient in Python, FastAPI, Hugging Face Transformers, and common MLOps stacks.
• Experienced in architecting secure, high-performance cloud systems (AWS/GCP), especially in regulated industries.
• Strategic thinker with a builder’s mindset—you love shipping production-ready systems that solve real-world problems.

Why Join N1 Healthcare?

• Own the tech vision of a fast-growing company transforming healthcare with AI.
• Build and scale real-world LLM systems that impact patient outcomes.
• Collaborate with world-class experts in medicine, genomics, and AI.
• Competitive compensation, equity, and remote/hybrid flexibility.
• Join a mission-driven team redefining longevity and personalized medicine.

To Apply:

Please apply with the following your resume and a video explaining one project in which you built a multi-agent LangChain system.

Include number and type of agents used, how agents communicated and passed data, memory and vector store choices, code samples or architecture diagrams, deployment stack, challenges faced and how you solved them, end-user outcomes and how success was measured.