Machine Learning Engineer – Voice AI, Generative Music

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

📋 Description

• Refine and enhance a singing-voice conversion and cloning model to achieve a minimum of 90% quality in blind listening evaluations.

• Accurately reproduce expressive vocal traits such as vibrato, falsetto, dynamics, and both spoken and sung delivery.

• Assess the expansion of the training dataset, alternative base models, and enterprise APIs that offer no-training guarantees.

• Take ownership of and enhance a Spanish-speaking Chatterbox Multilingual LoRA fine-tuning project.

• Guarantee precise reproduction of the Mexican accent and accurate pronunciation of J, Ñ, and X.

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

• Connect the inference endpoint to the existing web platform via an API.

• Train a second text-to-speech version using high-quality studio recordings.

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

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

• Incorporate the finalized lyrics model into the current frontend.

⛳️ Requirements

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

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

• Strong command of PyTorch.

• Hands-on experience with GPU cloud infrastructure such as RunPod or AWS.

• Familiarity with Docker and serverless inference.

• Proven 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: experience in singing-voice synthesis with ACE Studio, ACE-Step, RVC, so-vits-svc, or similar technologies.

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

🏝️ Benefits

• Security through client vetting to reduce risks and guarantee reliable, timely payments.

• Career support and guidance in finding new opportunities if a project isn't the right match.

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

• 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 instructors.

• Dedicated HR support.