Machine Learning Engineer – Voice AI, Generative Music

This is a fully remote position, open to applicants in Spain.

📋 Description

• Take charge of the complete machine-learning workflow, encompassing audio data preparation, training experiments, optimized inference, and production deployment.

• Enhance and refine a singing-voice conversion and cloning model to reach a minimum of 90% fidelity in blind listening assessments.

• Recreate expressive vocal qualities such as vibrato, falsetto, dynamics, spoken delivery, and sung delivery.

• Assess dataset expansion, alternative base models, and enterprise APIs with no-training guarantees.

• Manage an existing Chatterbox Multilingual LoRA fine-tune tailored for a Spanish-speaking voice.

• Ensure precise reproduction of a Mexican accent and accurate pronunciation of J, Ñ, and X sounds.

• Containerize and deploy the text-to-speech model as a serverless inference endpoint using RunPod or a comparable platform.

• Connect the inference endpoint to the current web platform through an API.

• Train a secondary text-to-speech version utilizing clean studio recordings to enhance output stability.

• Create a proprietary Spanish-language lyrics-generation model leveraging an open-weight LLM, LoRA fine-tuning, DPO, and RAG.

• Set evaluation standards and coordinate quality assessments with native Spanish speakers.

• Incorporate the finalized lyrics model into the existing frontend.

⛳️ Requirements

• Over 3 years of experience in training and deploying deep learning models in production, ideally within audio or NLP domains.

• Hands-on expertise in at least two of the following: Voice cloning or Singing Voice Conversion (SVC); Text-to-Speech model fine-tuning; LLM fine-tuning using LoRA, DPO, and RAG.

• Strong command of PyTorch.

• Practical experience with GPU cloud infrastructures such as RunPod or AWS, Docker, and serverless inference.

• Evidence-based model evaluation skills, including benchmarks, ablation studies, and blind testing.

• Native or strong professional proficiency in Spanish, essential for lyrics evaluation and voice quality assurance.

• Preferred: Background in music or experience with stems, MIDI, and DAWs.

• Preferred: Familiarity with ACE Studio, ACE-Step, RVC, so-vits-svc, or similar singing-voice synthesis technologies.

• Preferred: Experience with licensed celebrity or artist voices and consent-based voice AI.

🏝️ Benefits

• Security through client vetting to reduce risks and ensure reliability and prompt payments.

• Career support and assistance in finding new opportunities if a project does not align well.

• Legal assistance regarding independent contractor or sole proprietorship status, taxes, and related matters.

• English language courses.

• Opportunities for professional growth.

• Team-building activities.

• Flexible working hours.

• 29 days of paid time off (18 working days per year plus all national holidays).

• 10 paid recovery days.

• Comprehensive financial and legal support for independent contractors.

• Complimentary English classes with native speakers or Ukrainian educators.

• Dedicated HR support.