We are looking for an experienced Python Engineer – Data & ML Pipelines to develop, optimize, and maintain high-performance data processing and machine learning pipelines for digital pathology applications. The role focuses on building efficient and scalable processing workflows, integrating ML models into production systems, and preparing large training datasets, with a strong emphasis on performance optimization, memory efficiency, and code maintainability.
Job location: Remote / Serbia
Responsibilities
- Develop, optimize, and maintain Python-based data processing and machine learning pipelines
- Build and maintain efficient workflows for ML inference integration and training dataset preparation
- Identify, diagnose, and resolve performance bottlenecks in data processing pipelines
- Integrate machine learning models and algorithms into existing production workflows
- Develop and maintain scalable and reliable data processing components
- Work with cloud object storage services and S3-compatible APIs to support data processing workflows
- Refactor existing Python code to improve readability, maintainability, and reusability
- Organize shared functionality into reusable components to reduce code duplication
- Troubleshoot and resolve issues related to pipeline performance, memory consumption, and data processing
- Support the optimization of ML inference and dataset preparation workflows
- Document pipeline architecture, technical implementations, and key operational workflows
Requirements
- Strong professional experience with Python, including the development and maintenance of production data pipelines
- Hands-on experience with multithreading, multiprocessing, queues, and memory buffers
- Experience working with cloud object storage services and S3-compatible APIs
- Working knowledge of Linux environments and Git version control
- Strong problem-solving skills with a focus on performance optimization, code quality, and maintainability
- Excellent knowledge of English, both written and spoken
Nice to Have
- Experience with PyTorch, TorchVision, and CUDA
- Experience working with Google Cloud Platform (GCP) or Cloudflare R2
- Experience integrating machine learning inference workflows or preparing large-scale training datasets
- Familiarity with Google Cloud Healthcare API, DICOM stores, or medical imaging data
- Knowledge of SQL and relational databases, including MySQL