Our client is a healthcare revenue cycle analytics company that powers financial intelligence for over 45 major health systems across the US. Backed by a leading private equity firm, they are running a fast-moving, PE board-visible initiative to build a new generation of AI-native products on top of an advanced Claude Code-based orchestration environment.
We are looking for a Senior AI Engineer (Agentic Builder) to join their team. You will be a primary build force for a series of AI-native wedge products targeting healthcare revenue cycle workflows, building autonomous agents that execute real actions on clinical and financial data. Check it out!
Requirements
- 5+ years of software engineering experience, with the last 2+ years focused on AI-native product development.
- Hands-on experience with agentic frameworks and multi-agent orchestration (Claude Code, LangChain, LlamaIndex, or equivalent).
- Experience building autonomous action workflows.
- Full-stack capability: backend services, APIs, and lightweight frontend interfaces. Ability to take prototypes built in tools like Lovable or Codex into production.
- Experience with RAG pipelines, vector databases, and structured retrieval
- Token optimization and cost management in production AI systems.
- Familiarity with multi-LLM environments (Claude, OpenAI, etc.).
- Understanding of the shift from traditional RPA (Playwright, UiPath) toward agentic automation.
- Comfortable in CI/CD-style AI development pipelines with automated review loops, PR workflows, and GitHub-centric processes.
- Advanced English
- Healthcare industry background is a plus
Responsibilities
- Build and deploy production-ready AI-native wedge products within an existing Claude Code orchestration environment
- Take rapid product prototypes from the product team (built in Lovable, Claude, or Codex) and push them through to production
- Design and implement autonomous agent workflows that execute remediation actions on healthcare revenue cycle data
- Contribute to RAG pipeline design, vector database management, and intelligent retrieval architectures
- Participate in daily standups and async collaboration with a highly technical, fast-moving team
- Apply token optimization and cost-efficiency strategies in production AI systems
- Work across a multi-LLM stack and adapt tooling as the environment evolves
Opportunity
- Full-time contract
- Remote from LATAM
- Direct collaboration with a world-class team building the future of healthcare AI
- PST time zone overlap required
Interested? Share your resume with our Recruiters (apply@onbench.com) and schedule a confidential call for more details!