ML Engineer

We are looking for a Machine Learning Engineer to help advance our Optical Music Recognition (OMR) system. In this role, you will work at the intersection of deep learning and music technology, developing robust ML models, building scalable data pipelines, and contributing to research-driven innovation. If you are passionate about PyTorch, enjoy solving complex technical challenges, and are excited about applying AI to structured visual data like music notation — we’d love to hear from you.

We are actively integrating AI and automation into all areas of the business and expect candidates with mindset focused on improving efficiency and deliver a better user experience.

Key responsibilities

• Develop and enhance the OMR system’s core machine learning models using PyTorch.

• Collaborate with the Senior Research Engineer on prototyping, experimentation, and research-driven initiatives.

• Build and maintain dataset generation tools and automated data pipelines to support scalable model training.

• Work closely with the product team to understand users’ needs and translate them into technical solutions.

• Design, implement, and optimize inference APIs using FastAPI to efficiently serve model predictions.

• Maintain and improve Docker-based container environments to ensure scalable and reliable model deployment.

• Identify, debug, and resolve issues across the machine learning pipeline.

Required experience

• Proven experience developing and training machine learning models.

• Strong proficiency in Python and PyTorch.

• Solid understanding of music notation systems and their structural principles.

• Experience using Docker to containerize and deploy machine learning workloads.

Preferred:

• Experience with Vision-Language Models or image-to-sequence architectures.

• Experience designing and maintaining APIs using FastAPI.

• Experience using C++ to extend or optimize the underlying music processing library.

• Proficiency with Git and collaborative development workflows.