Senior ML Engineer, Voice Agents - Remote & Open-Source

Jobgether; Ireland; On-site; EUR 120,000 - 180,000; Full time

Benefits offered by this job

Remote work options

Health benefits

Parental leave

Company equity

Conferences/training budgets

Office visits in New York City and/or

Job summary

Jobgether is seeking a Senior Machine Learning Engineer, Voice Agents based in Ireland. You will own architecture of an open-source speech-to-speech library and drive integration of ASR, TTS, and end-to-end speech models for a production-ready voice platform.

You will lead API design, GPU inference, and real-time streaming, while collaborating with a global team to deploy to robotics and other real-world applications.

Qualifications

• Senior-level engineering experience with ownership of architecture.
• Experience building developer-facing infrastructure in AI/ML.
• Significant open-source contributions to a Python library and async Python.
• Strong understanding of distributed systems and failure modes.
• Proven experience shipping realtime tech with streaming or WebSockets/WebRTC.
• Production experience with LLMs or multimodal models.
• Strong written communication and collaboration skills.
• Genuine interest in voice technology and conversational AI.
• Contributions to voice-agent frameworks are a plus.
• Experience with llama.cpp or low-level inference runtimes is advantageous.
• Hands-on with ASR/TTS or end-to-end speech models; latency/quality trade-offs.
• GPU serving, quantization or on-device inference is advantageous.
• Knowledge of audio pipelines (VAD, echo cancellation, jitter buffering).
• Experience deploying tech to embedded/robotics environments is beneficial.
• Public technical track record through talks or blogs is valued.
• Candidates may apply even if not meeting every requirement.

Responsibilities

• Take architectural ownership of major parts of the open-source speech-to-speech library.
• Integrate ASR, TTS, and end-to-end speech models with clean abstractions.
• Review contributions, triage issues, manage releases, grow the community.
• Design developer API and streaming protocol for the voice platform.
• Build and operate serving infrastructure for realtime GPU inference.
• Collaborate with Hub and inference teams to enable easy integration.
• Move platform from prototype to production with load testing and SLOs.
• Create documentation, examples and templates for developers.
• Support deployments including robotics fleet and existing tech.
• Contribute to wider ML/AI community through talks or blogs when desired.

Skills

Open-source contributions

Asynchronous Python

Distributed systems

LLMs / multimodal models

GPU serving

Tools

WebSockets

WebRTC

GPU inference

Job description

Jobgether is seeking a Senior Machine Learning Engineer, Voice Agents based in Ireland. You will own architecture of an open-source speech-to-speech library and drive integration of ASR, TTS, and end-to-end speech models for a production-ready voice platform.

You will lead API design, GPU inference, and real-time streaming, while collaborating with a global team to deploy to robotics and other real-world applications.