Machine Learning Engineer – Voice AI, Generative Music

Job not on LinkedIn

🔥 17 hours ago

🇺🇸 United States – Remote

⏱ Part Time

🟡 Mid-level

🟠 Senior

🤖 Machine Learning Engineer

👻 Ghost score 25%

What it means: how likely this posting is sitting open without active hiring.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

MWDN

WebsiteLinkedInAll Job Openings

51 - 200 employees

💼 Consulting

📦 Logistics

🏥 Healthcare

Consulting • Logistics • Healthcare

MWDN is a comprehensive IT services company that specializes in software development, web design, mobile development (iOS and Android), and desktop development. With over 200 in-house software engineers, MWDN provides a range of services including staff augmentation, dedicated teams, and global IT recruitment. Operating globally with delivery centers in Central and Eastern Europe, MWDN effectively bridges businesses in the USA, Europe, and Israel to top-tier tech talent while focusing on cost-effective solutions and personalized services tailored to client needs.

📋 Description

• 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