Who We Are Were building tools that help healthcare teams work faster and smarter. Our software handles the tedious parts of patient care coordination so that clinicians can focus on patients. We ship fast, iterate constantly, and believe AI should amplify human capability, not replace it.
The Role Youll own the intelligence layer of our platform—the orchestration systems that coordinate LLM calls, the retrieval pipelines that surface relevant medical history, and the evaluation frameworks that keep it all honest.
Youre a generalist who can and will ship across the stack, but you geek out on AI infrastructure. Youve opinions on prompt management, youve debugged token limits at 2am, and you know that "it works in the playground" means nothing. Youre pushing the limits of your bot swarm farther every day to maximize your impact and excited for the future.
You might:
Improve our LangGraph orchestration to handle complex clinical workflows
Build retrieval pipelines that search patient records using embeddings and vector similarity
Set up Langfuse/LangSmith tracing to debug why a summarization chain is hallucinating
Fine-tune a model on medical terminology or clinical note structure
Evaluate Gemini vs Claude vs GPT for specific healthcare tasks
Design the data pipeline that turns unstructured clinical docs into searchable vectors reliably and responsibly
Write the TypeScript or Python service(s) that ties it all together
You Should Have Hands‑on LLM experience. Youve built with OpenAI, Anthropic, or Google APIs. You understand context windows, temperature, and when to use which model.
Orchestration chops. LangChain, LangGraph, or similar. You know how to chain calls, handle failures, and manage state.
Observability instincts. Youve used Langfuse, LangSmith, or Phoenix. You know that production AI without tracing is flying blind.
Strong hold of agentic code authoring systems. You are pushing the limits of Claude, Codex, Gemini, Copilot, or similar daily.
Retrieval/RAG experience. Youve built vector search with Pinecone, Weaviate, pgvector, or Vertex AI Matching Engine. You understand chunking strategies, embedding models, and reranking.
Generalist coding ability. You can write Python for ML pipelines and TypeScript for services. Youre not afraid of infrastructure and youre not too caught up in the moment to pitch in on the boring stuff.
Bonus Points Fine‑tuning experience (LoRA, PEFT, or full fine‑tunes)
Healthcare/FHIR/clinical data background
Experience with Gemini models and Vertex AI
Evaluation frameworks (RAGAS, custom evals, human‑in‑the‑loop)
Youve made embeddings work on messy, real‑world data
Tech Stack AI/ML: LangGraph, Vertex AI, Gemini, embeddings, vector search
Observability: Langfuse, LangSmith
Backend: Python (FastAPI), TypeScript (Fastify)
Data: PostgreSQL, BigQuery, FHIR
Infrastructure: GCP (Cloud Run, Pub/Sub), Terraform
What We Offer Competitive salary + equity
Health insurance (were a healthcare company—we get it)
Remote‑first, async‑friendly
Small team where your work ships to production, not a backlog
Basalt Health is an equal opportunity employer.
We are only able to consider candidates who are already authorized to work in the United States without employer sponsorship. #J-18808-Ljbffr