Staff AI Engineer (Remote, Latin America)

About the role

We are seeking a Staff (or strong Senior) AI Engineer to own the AI spine of a real‑time conversational voice platform for a market‑leading conversation‑intelligence company. This remote, individual‑contributor position will lead the design, implementation, and evaluation of a production‑grade voice role‑play engine.

Key responsibilities

• Design and build the real‑time voice role‑play runtime, managing latency, turn‑taking, barge‑in, and voice activity detection.
• Develop a hybrid task‑evaluation pipeline that combines deterministic rules with an LLM‑as‑judge calibrated against human labels.
• Create an automated evaluation and regression harness, including golden‑set scenarios, CI quality gates, and drift monitoring.
• Implement a config‑driven persona generator with versioned prompts separate from code.
• Integrate speech‑to‑text, speaker timing, and call‑summary generation, and enforce moderation guardrails.

Required profile

• Proven experience building production real‑time voice AI systems.
• Deep understanding of speech‑to‑text, text‑to‑speech, and large language model integration.
• Strong background in building evaluation pipelines and CI/CD quality controls.
• Full professional proficiency in English.
• Ability to work autonomously in a remote, high‑seniority squad.

Required skills

• OpenAI Realtime API (or equivalent real‑time speech APIs)
• Speech‑to‑Text (STT) integration
• Text‑to‑Speech (TTS) pipelines
• Large Language Models (LLM) for generation and judging
• Voice Activity Detection (VAD) and turn‑taking logic
• CI/CD pipelines and regression testing
• Model drift monitoring

What we offer

• Opportunity to shape a core AI component for a high‑impact SaaS product.
• Fully remote work within Latin America.
• Collaboration with a senior, high‑performance engineering squad.