MLOps Engineer in SINGAPORE

Wubble.ai is a pioneering Music AI platform redefining the future of music generation. Our proprietary foundation model pushes the boundaries of AI-driven music creation. We’re proud to work with top-tier global clients, including Disney, Starbucks, Microsoft, HP, and more. Backed by industry giants like Antler, Google, NVIDIA, and others, we are ranked as one of the top 5 startups in Asia!

Role Overview

We are looking for a Contract MLOps Expert with deep experience in CUDA kernel optimization to enable concurrent inference requests on our advanced music generation model. This is a high-impact role where you will directly influence the scalability and performance of our platform.

Key Responsibilities

1. CUDA Kernel Optimization : Analyze the existing CUDA kernel implementation and introduce concurrency optimizations to handle multiple requests efficiently.
2. High-Performance Computing (HPC): Utilize parallel computing techniques and GPU best practices to maximize throughput and minimize latency.
3. MLOps & Integration : Collaborate with engineering teams to integrate optimized kernels into our production environment and CI/CD pipelines.
4. Performance Benchmarking : Design and run performance tests to measure the improvements from your optimizations.
5. Documentation & Knowledge Transfer: Provide clear technical documentation and best practices for ongoing maintainability.

Qualifications

• GPU & CUDA Expertise : Demonstrated experience in writing, debugging, and optimizing CUDA kernels at scale. Familiarity with concurrency, memory management, and parallelization strategies for GPU-accelerated applications.
• MLOps & ML Frameworks : Hands-on experience with MLOps workflows, CI/CD, and containerization (Docker, Kubernetes). . Proficiency in at least one deep learning framework (e.g., PyTorch).
• High-Scale Model Inference : Experience optimizing large-scale model inference pipelines for real-time or near real-time use cases.
• Problem-Solving & Communication
• Strong analytical skills for troubleshooting performance bottlenecks.
• Ability to communicate technical solutions clearly to both technical and non-technical stakeholders.
• Experience with H100 or similar high-end GPU architectures.
• Familiarity with large language or generative models in the music or media domain.

Why Join Wubble.ai?

• Elite Client Portfolio: Work on solutions that power the creative experiences of world-renowned brands like Disney, Starbucks, Microsoft, and HP.
• Top-Tier Backing: We’re supported by industry leaders such as Antler, Google, and NVIDIA, offering you the opportunity to collaborate with a well-funded and visionary team.
• Cutting-Edge Tech: Contribute to an advanced foundational model pushing the envelope in AI-driven music generation.
• High Impact, High Reward: Your expertise will directly shape the performance and scalability of a groundbreaking platform—this is not your everyday startup gig.
• Remote Collaboration: Enjoy the flexibility of a fully remote contract, enabling you to collaborate from anywhere while tackling exciting, high-profile challenges.

Contract Details

• Contract Type: Contract / Consultancy
• Duration: 1 month, with potential extension based on project needs
• Compensation: Competitive rate, commensurate with experience

How to Apply

Send your resume, portfolio, and a brief cover letter highlighting relevant CUDA optimization and MLOps experience to sufi@wubble.ai with the subject line: "MLOps Expert – CUDA Kernel Optimization Application"

Join Wubble.ai and help us orchestrate the future of music through unparalleled AI innovation!