5 дней назад
Voice AI Engineer
Вакансия из Hirify Global, списка международных tech-компанийДля мэтча и отклика нужен Plus
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Voice AI Engineer (Python/LLM): Building real-time AI voice agents for phone and web conversations with an accent on turn-taking, low-latency speech pipelines, GPU model serving, and conversational model optimization. Focus on reducing end-to-end audio latency, fine-tuning speech and language models, enabling provider failover, and designing evaluation systems for production call quality.
Location: Remote within the European Union; candidates must be located in Greece, Germany or Austria
Company
GmbH is a Swiss startup building AI voice agents that handle business phone calls and web conversations while integrating with telephony and business tools.
What you will do
- Improve conversational turn-taking, voice activity detection, and end-of-turn detection for live calls.
- Reduce end-to-end latency across speech recognition, language models, and speech synthesis, including seamless provider failover.
- Optimize LLM conversation workflows through prompting, tool calls, streaming, and speculative or parallel requests.
- Serve proprietary speech recognition and synthesis models on GPUs while measuring throughput and time to first audio.
- Fine-tune speech and language models for customer languages and voices.
- Build test calls, benchmarks, and quality metrics to evaluate production changes.
Requirements
- Senior or strong mid-level engineering experience with production systems involving real-time audio, conversational AI, or ML model serving.
- Strong Python skills, including asyncio and streaming pipelines.
- Hands-on experience with STT, TTS, VAD, and LLM APIs in latency-sensitive systems.
- Experience serving models on GPUs, such as with vLLM or similar tools, including batching and memory-limit fundamentals.
- English proficiency is essential; English is the working language.
- Data-driven ownership of problems from diagnosis through production fixes.
Nice to have
- Experience with LiveKit Agents, pipecat, or WebRTC.
- Speech or language model fine-tuning with LoRA or full fine-tuning.
- Audio signal processing, including echo cancellation or noise suppression.
- German language skills or experience with German-language speech data.
Culture & Benefits
- Flexible remote work or access to a co-working space.
- Company laptop and phone provided.
- Small, agile, collaborative team with direct impact on the product.
- Opportunity to work across the voice stack, from model serving to the caller experience.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →