Senior Machine Learning Data Pipeline & Backend Engineer (m/f/d)

We are seeking a Senior Machine Learning Data Pipeline & Backend Engineer (m/f/d) to drive the development of multimodal data pipelines, scalable inference services, and cloud?based ML infrastructure for cutting?edge generative AI applications. You will work across data engineering, backend development, and cloud deployment to ensure high?quality training datasets, reliable inference endpoints, and robust production environments.

Responsabilities:

• Build data preparation pipelines for multimodal training data (images, segmentation masks, depth data, 3D assets)
• Prepare and validate datasets across modalities and technical requirements
• Develop REST APIs using Ray Serve for model inference
• Integrate SQL databases for data access and persistence
• Deploy workloads as standalone jobs, backend services, or AWS?based executions
• Use AWS services (S3, EC2, IAM) for storage, compute, and permissions
• Leverage AWS Bedrock for managed model inference and AWS Agentcore for AI agent workloads
• Run PyTorch inference workloads and optimize ML execution
• Manage Python environments and dependencies across deployment targets

Skills:

• Strong experience in Python, data processing, ML pipelines, and backend engineering
• Hands?on expertise with multimodal data and 3D asset processing
• Practical experience with Ray Serve, SQL, and AWS cloud services
• Deep knowledge of PyTorch, inference workflows, and GPU?based environments
• Ability to independently design, implement, and operate production?grade ML systems

Key Details:

• Location: Herzogenaurach / remote
• Start Date: asap
• Duration: 6 months
• Workload: 100 %
• Remote Share: 60 %
• Languages: English (fluent), German as a plus