AI Application & Backend Core Delivery: Engineer and iterate realtime voice AI services and Agent workflows; build key modules including tool orchestration, memory, and multi-step reasoning; translate business requirements into scalable service capabilities.

Production-Grade System Engineering: Design and implement highly-available, low-latency, scalable architectures (latency is especially critical for realtime voice); establish monitoring, logging, alerting, and tracing foundations to support both high-frequency consumer usage and enterprise deployment.

AI Integration & Closed-Loop Iteration: Integrate LLM / ASR / TTS capabilities into product pipelines; help build evaluation frameworks and automated testing for Agent and voice quality; partner with Applied AI and Product to drive data-driven, closed-loop improvement in production.

Full-Stack Collaboration & Rapid Iteration: Keep backend as your main line while extending into mobile, SDK, or frontend surfaces as needed to ship end-to-end; collaborate closely with Product, Applied AI, and mobile teams across enterprise PoCs and consumer features.

AI-Native Engineering Velocity: Actively adopt AI coding assistants, agentic dev workflows, and automated testing/debugging tools to accelerate iteration while maintaining strong engineering quality.

Full-Stack Engineer - Palo Alto

Responsibilities

Qualification

Required

Benefits

Company

Plaud

More roles at Plaud