The posting
About Sage Care
Sage Care is a fast-growing, early-stage healthcare startup founded by exceptional leaders from Apple, Uber, Carbon Health and backed by top-tier venture capital (General Catalyst, Chelsea Clinton). With a strong customer pipeline, Sage Care is transforming healthcare by simplifying care navigation.
Our platform makes it easier for patients to find the right doctor, helps providers focus on those who need them most, and ensures faster access to care, delivering better care and stronger economic outcomes at scale through harnessing the latest AI innovations.
Building on our successful collaborations with health systems across the U.S., we have expanded internationally to the MENA region. We are now partnering with health systems there to deploy our AI-powered care navigation platform.
About the Role
Our AI voice agents handle real patient conversations for hospital systems in production today. At the core of every conversation is the agent platform: the reasoning, orchestration, tool use, and control-flow systems that determine how an agent behaves in a live call.
We are hiring a Software Engineer to own this platform. Your mission is to make LLM-powered reasoning scale: consistent, observable, and reliable under real production load, across thousands of conversations where the model is non-deterministic but the outcome cannot be.
This is a deeply hands-on role. You will write code, debug production issues, and make the foundational architecture decisions that other engineers build on. You will work alongside the engineers who own our real-time voice and telephony infrastructure; they own how audio moves, you own how agents think and act.
What You'll Do
- Design and own the agent platform architecture: orchestration, tool use, and control flow
- Build the systems that let agents operate reliably across real-world patient interactions
- Make multi-step reasoning dependable: workflow selection, tool coordination, failure handling, and recovery
- Debug and resolve complex production issues (edge cases, failures, regressions) in non-deterministic systems
- Optimize performance across the stack (latency, cost, reliability)
- Define the patterns and best practices for how Sage builds and operates AI agents
- Mentor engineers and raise the bar on AI systems design and execution
What We're Looking For
Required
- 7+ years of software engineering experience
- Experience building and operating production AI systems (agents, conversational systems, or ML-powered workflows) that handle real user interactions end-to-end
- Strong understanding of: agent orchestration and tool use multi-step workflows and control flow LLM behavior in real-world settings
- Strong debugging skills across complex, non-deterministic systems
- Experience working with systems where latency, correctness, and reliability matter simultaneously
- Demonstrated experience owning systems in production: on call, debugging incidents, and improving systems based on real usage
Nice to Have
- Experience with voice systems (speech-to-text, text-to-speech, real-time pipelines)
- Experience building agent harnesses, orchestration layers, or execution frameworks
- Experience optimizing low-latency / real-time AI systems
- Experience working with multiple model providers or inference stacks
- Experience in healthcare or other safety-critical, regulated domains
What Success Looks Like
- Agents that handle real-world patient interactions reliably and predictably
- Clear, scalable agent architecture (not ad-hoc or fragile systems)
- Reasoning that holds up as we add partners, use cases, and call volume
- Fast identification and resolution of production issues
- Systems that balance flexibility (AI) with control (engineering)
- Patterns that make every engineer at Sage better at building agents
