Audio AI Engineer bei Propio

Description

Propio is on a mission to make communication accessible to everyone. As a leader in real-time interpretation and multilingual language services, we connect people with the information they need across language, culture, and modality. We’re committed to building AI-powered tools to enhance interpreter workflows, automate multilingual insights, and scale communication quality across industries.

We are hiring an Audio AI Engineer that will develop and optimize end-to-end systems that enable real-time, high-fidelity speech-to-speech interpretation at Propio. This role focuses on seamlessly connecting speech recognition, translation, and synthesis technologies to create natural, low-latency interpretation experiences. 

Key Responsibilities:

• Design and optimize end-to-end Speech-to-Speech pipelines that integrate ASR, translation, and TTS with minimal latency
• Build bidirectional interpretation systems that handle turn-taking, speaker identification, and context preservation across language boundaries 
• Collaborate with the Audio/Speech Engineer to optimize latency, quality, and robustness of speech components in the full pipeline
• Work with the Staff ML Engineer to design efficient inference architectures and deployment strategies for real-time streaming systems
• Develop streaming ASR and TTS systems capable of handling continuous, overlapping speech in interpretation scenarios
• Benchmark and optimize latency across all pipeline stages (speech capture, recognition, translation, synthesis)
• Integrate speaker diarization, acoustic environment adaptation, and speech enhancement into interpretation workflows
• Partner with linguists and product teams to validate interpretation quality and gather domain-specific feedback

Requirements

Qualifications:

• Bachelor's or Master’s Degree in Electrical Engineering, Computer Science, or related field
• 3+ years of experience in speech processing, audio engineering, or conversational AI systems
• Deep expertise in ASR, TTS, and streaming audio architectures
• Proficiency in Python, ML frameworks, and experience with real-time signal processing 
• Experience building low-latency production systems and optimizing for inference performance
• Strong understanding of interpretation workflows, multilingual challenges, and speech quality metrics

Preferred Qualifications:

• Experience building speech-to-text pipelines or hybrid ASR + LLM systems
• Familiarity with real-time audio processing or latency-sensitive applications

#LI-JS1