Voice AI Engineer arbeitnow NAIRON Berlin · 10/18/2026

Primetime; Berlin; Hybrid; EUR 85.000 - 120.000; Vollzeit

Zusammenfassung

Nairon GmbH is seeking a Voice AI Engineer to make our agents sound fast, natural and reliable in live calls. You will tackle end-to-end latency, latency-sensitive systems, and real-time audio processing across STT, TTS and LLM integrations.

You will work with GPUs (e.g., vLLM), fine-tune models for multiple languages, and improve evaluation metrics. This remote role accepts candidates from Greece, Germany or Austria, with English as working language.

Qualifikationen

• 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.
• Fine-tuning (LoRA or full) of speech or language models.
• Audio signal processing such as echo cancellation or noise suppression.
• German, or experience with German-language speech data.
• English proficiency is essential, both written and spoken.

Aufgaben

• Improve turn-taking and latency in live calls, including voice activity and end-of-turn detection.
• Cut end-to-end latency across speech recognition, language models and synthesis; seamless failover.
• Optimise use of LLMs in conversation, including prompting and tool calls.
• Serve speech models (STT and TTS) on GPUs and measure throughput and time to first audio.
• Fine-tune models for customers' languages and voices.
• Build evaluation, test calls, benchmarks and quality metrics.

Kenntnisse

Python (asyncio)

Streaming pipelines

Latency-sensitive systems

Speech APIs

LLM APIs

Tools

vLLM

GPU model serving

LiveKit

pipecat

WebRTC

Jobbeschreibung

For this position we are only looking for candidates located in Greece, Germany or Austria.

Nairon GmbH is a Swiss startup building AI voice agents that answer and make phone calls for businesses. Our platform runs real-time conversations over the phone and on the web, connected to our customers' telephony and business tools. We value clear communication, thoughtful engineering, and a collaborative approach to problem-solving. Join us as we continue to develop tools that make a difference.

Tasks

As a Voice AI Engineer at Nairon GmbH, you will make our agents sound fast, natural and reliable in live calls. Your responsibilities will include:

• Improving turn-taking: when the agent speaks, waits, yields or gets interrupted, including voice activity and end-of-turn detection.
• Cutting end-to-end latency across speech recognition, language models and speech synthesis, and making provider failover seamless.
• Optimising how we use LLMs in conversation: prompting, tool calls, streaming and speculative or parallel requests.
• Serving our own speech models (STT and TTS) on GPUs, measuring throughput and time to first audio.
• Fine-tuning speech and language models for our customers' languages and voices.
• Building evaluation: test calls, benchmarks and quality metrics that tell us when a change really helps.

Requirements

Experience:

A senior or strong mid-level engineer with production experience in real-time audio, conversational AI or ML model serving.

Technical Skills:

Required:

• 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.
• Fine-tuning (LoRA or full) of speech or language models.
• Audio signal processing such as echo cancellation or noise suppression.
• German, or experience with German-language speech data.

Communication:

• English proficiency is essential, both written and spoken, as it is the working language for all positions.

Soft Skills:

• You measure before and after, and trust numbers over impressions.
• Ownership of a problem from the first bad call to the fix in production.
• Flexible Work Setup: Work fully remotely or from a co-working space - whichever suits you best.
• Equipment Provided: Company laptop and phone provided for all employees.
• Collaborative Environment: Join a small, agile team where your contributions have a direct impact.
• Growth Opportunities: Work across the whole voice stack, from model serving to the conversation the caller hears.

Closing

If you want to make AI conversations feel human on a real phone line, we'd love to hear from you.

This overview was written from the original listing to help you understand the role. Always confirm the specifics on the employer's application page.