Remote Voice AI Engineer: Real‑Time Speech & LLM

NAIRON GmbH; Kreuzlingen; Remote; CHF 120,000 - 170,000; Full time

Benefits offered by this job

Flexible work setup

Company laptop and phone

Collaborative environment

Growth opportunities

Job summary

Nairon GmbH is a Swiss startup building AI voice agents that handle live calls and web interactions for businesses. We seek a senior engineer to make our agents sound fast, natural, and reliable in real-time conversations.

You will optimize latency, streaming pipelines, and prompts for efficient LM usage, while maintaining high reliability across GPUs and speech components. English is the working language; German-language data experience is a plus.

Qualifications

• Senior or strong mid-level engineer with production experience in real-time audio, conversational AI or ML model serving.
• Strong Python, including asyncio and streaming pipelines.
• Hands-on work with speech (STT, TTS, VAD) and LLM APIs in latency-sensitive systems.
• Model serving on GPUs, for example with vLLM or similar, and the basics of batching and memory limits.
• Nice to have: LiveKit Agents, pipecat or WebRTC.
• German, or experience with German-language speech data.
• English proficiency is essential, both written and spoken, as it is the working language for all positions.

Responsibilities

• Improve turn-taking: voice activity and end-of-turn detection in live calls.
• Reduce end-to-end latency across STT, LLMs and TTS.
• Optimize prompting, tool calls, streaming and parallel requests in LLM usage.
• Serve our own speech models on GPUs and measure throughput.
• Fine-tune speech/language models for customer languages and voices.
• Build evaluation: test calls, benchmarks and quality metrics.

Skills

Python asyncio

Streaming pipelines

Speech (STT TTS VAD)

LLM APIs

GPU model serving

vLLM

Latency optimization

Tools

LiveKit

WebRTC

pipecat

Job description

Nairon GmbH is a Swiss startup building AI voice agents that handle live calls and web interactions for businesses. We seek a senior engineer to make our agents sound fast, natural, and reliable in real-time conversations.

You will optimize latency, streaming pipelines, and prompts for efficient LM usage, while maintaining high reliability across GPUs and speech components. English is the working language; German-language data experience is a plus.