Редкий шанс возглавить разработку важной части AI-экосистемы в Hugging Face, совмещая архитектурные задачи с самыми свежими технологиями в области Voice AI.
?Зарплата не указана
Передовой стек
Трендовый домен
Прозрачный уровень ответственности
Компания-лидер
Отличные бонусы
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior Engineer (Voice AI): Building Hugging Face’s open voice-agent stack, including the speech-to-speech library and hf-voice product, with an accent on realtime inference, developer APIs, and open-source infrastructure. Focus on designing streaming protocols, serving voice models on GPUs, managing concurrency and autoscaling, and taking the platform from demo to production reliability.
Location: Remote
Company
Hugging Face builds an open platform and open-source tools for AI developers, including models, datasets, applications, and machine learning infrastructure.
What you will do
Own the architecture of the open-source speech-to-speech library, including pipeline design, latency budgets, and realtime-loop reliability.
Integrate ASR, TTS, and end-to-end speech models while maintaining clean abstractions.
Design hf-voice developer APIs and streaming protocols covering session lifecycle, WebSockets/WebRTC transport, authentication, errors, and versioning.
Build realtime GPU inference serving with concurrency, autoscaling, observability, and cost optimization.
Take the product from demo to production through load testing, SLOs, and graceful degradation.
Write documentation and examples, support Reachy Mini deployments, and collaborate with the Hub, inference, and open-source communities.
Requirements
Senior engineering experience with autonomous ownership of substantial architecture.
Experience building developer-facing infrastructure for AI or developer tools, such as inference APIs or agent infrastructure.
Substantial open-source contributions to a Python library and comfort with async Python and distributed systems.
Experience shipping realtime systems involving streaming, WebSockets, WebRTC, audio, video, or live inference.
Production experience with LLMs or multimodal models, plus clear written communication and asynchronous collaboration.
Strong motivation to work on voice and conversational AI.
Nice to have
Contributions to voice-agent frameworks or low-level inference runtimes.
Experience with ASR, TTS, speech-model evaluation, GPU serving, quantization, or on-device inference.
Audio pipeline knowledge, including VAD, echo cancellation, jitter buffers, barge-in, and turn detection.
Experience shipping to embedded or robotics targets and a public record of talks, blog posts, or demos.
Culture & Benefits
Remote options, flexible working hours, and a distributed workplace with offices in NYC and Paris.
Health, dental, and vision benefits for employees and dependents.
Parental leave, flexible paid time off, and workstation equipment when needed.
Reimbursement for relevant conferences, training, and education.
Company equity for employees and support for diversity, equity, and inclusion.
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 →