Build LLM and voice-powered experiences that help patients and providers get answers faster, with safety and reliability baked in. This role is for an engineer who can take AI from prototype to production and keep it solid under real-world traffic.
About Fabric Health
Fabric Health is solving healthcare’s biggest bottleneck: clinical capacity. They unify the care journey from intake to treatment using intelligent automation so clinicians can focus on patients, not admin work. They’re trusted by major health systems and backed by top-tier investors.
Schedule
• Full-time, remote
• Cross-functional work with product, medical, and engineering teams
• Cloud-native deployment expectations (AWS + Kubernetes)
• Hands-on build role: prototype to production
What You’ll Do
⦁ Design, build, and optimize LLM applications (RAG, classification, summarization, fine-tuning)
⦁ Prototype and productionize AI/ML features in Python and integrate them with backend services
⦁ Partner with product and medical teams to implement safeguards and business constraints for AI outputs
⦁ Build APIs that enable other product components to reliably use LLM applications
⦁ Create automated evaluations to measure accuracy, safety, and performance of LLM-powered systems
⦁ Maintain and improve existing NLP and AI diagnosis components in production
⦁ Develop analytics and monitoring to track performance and prioritize improvements
⦁ Deploy AI services end-to-end in cloud-native environments using AWS and Kubernetes
⦁ Research and test new AI tools, APIs, and architectures to keep systems current and effective
⦁ Contribute to Fabric’s conversational AI strategy across voice and digital channels
What You Need
⦁ 5+ years of software engineering or applied ML experience building real-world AI/ML systems
⦁ Strong Python backend proficiency (Flask or FastAPI) and 3+ years of hands-on LLM/agent experience
⦁ Solid understanding of embeddings and vector/embedding databases
⦁ Experience with NLP or speech processing technologies (ASR/TTS a plus)
⦁ Familiarity with modern AI/ML frameworks and tools (Hugging Face, OpenAI API, LangChain, LangGraph)
⦁ Experience deploying cloud-native applications on AWS with Kubernetes and containers
⦁ Proven ability to bring models from research to production with latency, scale, and reliability in mind
⦁ Strong communication skills and comfort collaborating across technical and non-technical teams
Benefits
⦁ Salary range: $150,000–$190,000 per year (based on market, experience, and qualifications)
⦁ Comprehensive benefits package may include medical, dental, vision, unlimited PTO, and a 401(k)
⦁ Potential additional compensation eligibility (stock options and bonuses)
If you’re ready to build responsible, production-grade healthcare AI that actually improves access and outcomes, this is your shot.
Happy Hunting,
~Two Chicks…