Clera
AI Engineer
About this role
Join a healthtech startup as an AI Engineer to build and maintain patient-facing conversational AI systems for medical tourism. You'll own the full stack of LLM agent infrastructure, diagnose production failures, and balance technical excellence with patient empathy in a high-impact role.
What you'll do
- Debug and fix AI conversation failures with patients, shipping code solutions to prevent recurrence
- Build and maintain agent infrastructure including tool integrations, evaluation frameworks, and retrieval systems
- Automate recurring manual workflows on the clinic side to reduce operational toil
- Provide direct patient support with empathy when AI systems fall short, converting those insights into product improvements
- Own systems end-to-end with minimal oversight, making independent architectural decisions
What they're looking for
- LLM and agent systems (design, building, and shipping)
- Python or equivalent backend language
- Agent infrastructure (evals, RAG/retrieval, tool integrations)
- Production debugging and diagnostics for LLM systems
- Vector databases and embedding systems
- Prompt engineering and conversational AI evaluation
- Startup autonomy and independent system ownership
- Patient communication and empathy
Benefits
- Base salary $150,000–$200,000 annually
- Fully on-site role in San Francisco with no remote flexibility
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Clera
Clera builds an agentic operating system that automates complex workflows and processes through AI agents, with a platform designed to simplify distributed infrastructure management for developers. The company is hiring Founding Engineers, Customer Engineers, and Product Engineers to develop both backend systems and user-facing interfaces across their AI automation products.
View all jobs at CleraLikely interview questions
- Describe a time you diagnosed and fixed a failure in a production LLM or agent system. What was your debugging process?
- Walk us through how you've built a RAG system or retrieval-based agent from scratch. What challenges did you encounter?