Software Engineer, Agent Platform
Palo Alto, CA, United StatesAll locationsPalo Alto, CA, United StatesHQ Hybrid
$200,000–$250,000 a yearJobFig found this opening at its original source and checks that it remains available.
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 bring
- 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
- 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
- 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