Staff AI Engineer, Voice Agents

About The Role

We’re hiring a Staff AI Engineer to lead the design and evolution of Sage Care’s AI agents, with a focus on voice systems. This role focuses on building and operating AI agents that perform reliably in real-world conditions. You’ll own how our agents behave end-to-end: from orchestration and tool use to latency, evaluation, and failure handling. This is a hands-on role. You will write code, debug production issues, and directly improve systems.

What You’ll Do

• Design and own AI agent architecture (orchestration, tool use, control flow)
• Build systems that enable agents to operate reliably across real-world interactions
• Develop and improve evaluation frameworks for agent quality and behavior
• Debug and resolve complex issues in production (edge cases, failures, regressions)
• Optimize performance across the stack (latency, cost, reliability)
• Define patterns and best practices for building and operating AI agents
• Mentor engineers and raise the bar on AI systems design and execution

Required

• 7+ years of software engineering experience
• Experience building and operating user-facing, real-time production systems
• Experience building 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
• Experience designing evaluation systems for AI quality
• Strong debugging skills across complex, non-deterministic systems
• Experience working with systems where latency, correctness, and reliability matter simultaneously (e.g. real-time decisioning, interactive systems, or high-throughput services)
• Demonstrated experience owning systems in production: including on call, debugging incidents, and improving systems based on real usage
• The role is very specific: someone who wants to push the edge of what voice AI agents can do and turn that into a real product. That means staying on top of the latest research in voice/agent systems and rapidly building POCs, then bringing those ideas into production by aligning the team and productizing what works.
• The role sits right at the intersection of research, product, and systems.

Nice to Have

• Experience with voice systems (speech-to-text, text-to-speech, real-time pipelines)
• Experience building customer support agents or similar systems
• Experience optimizing low-latency / real-time AI systems
• Experience working with multiple model providers or inference stacks