Machine Learning Engineer – Voice AI, Generative Music
Posted 2ds ago
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
Part-time ML Engineer building voice-cloning, text-to-speech, and Spanish lyrics-generation systems. Deploying production AI models for an AI-native music label’s music pipeline.
Responsibilities:
- Fine-tune and improve a singing-voice conversion and cloning model
- Increase vocal fidelity from a 70–75% baseline to at least 90% in blind listening tests
- Reproduce expressive vocal characteristics including vibrato, falsetto, dynamics, spoken delivery, and sung delivery
- Evaluate training dataset expansion, alternative base models, and enterprise APIs
- Own and improve a validated Chatterbox Multilingual LoRA fine-tune for a Spanish-speaking voice
- Ensure accurate Mexican-accent reproduction and pronunciation of J, Ñ, and X
- Containerize the text-to-speech model and deploy it as a serverless inference endpoint using RunPod or similar
- Integrate the inference endpoint with the existing web platform through an API
- Train a second version using clean studio recordings to improve output stability
- Develop a proprietary Spanish-language lyrics-generation model
- Use an open-weight LLM, LoRA fine-tuning, DPO preference optimization, and RAG over a curated content corpus
- Establish evaluation criteria and organize quality assessment with native Spanish speakers
- Integrate the completed lyrics model into the existing frontend
Requirements:
- 3+ years of experience training and deploying deep learning models in production, preferably within audio or NLP
- Hands-on experience in at least two of: voice cloning or Singing Voice Conversion (SVC); Text-to-Speech model fine-tuning; LLM fine-tuning using LoRA, DPO, and RAG
- Strong proficiency in PyTorch
- Practical experience with GPU cloud infrastructure such as RunPod or AWS
- Experience with Docker and serverless inference
- Rigorous, evidence-based model evaluation, including benchmarks, ablation studies, and blind testing
- Native or strong professional proficiency in Spanish, required for lyrics evaluation and voice quality assurance
- Music background or experience with music-production tools and workflows, including stems, MIDI, and DAWs (nice to have)
- Experience with singing-voice synthesis solutions such as ACE Studio, ACE-Step, RVC, so-vits-svc, or similar technologies (nice to have)
- Experience working with licensed celebrity or artist voices and consent-based voice AI (nice to have)
Benefits:
- Security through client vetting to minimize risks and ensure reliability and timely payments
- Career support and assistance finding new opportunities
- Legal assistance with independent contractor or sole proprietorship status, taxes, and related processes
- English courses
- Professional growth opportunities
- Team-building events
- Flexible working hours
- 29 days of PTO (18 working days per year plus all national holidays)
- 10 paid recovery days
- Full financial and legal support for independent contractors
- Free English classes with native speakers or Ukrainian teachers
- Dedicated HR support



















