Senior ML Infrastructure / MLOps Engineer (m/w/d)

We are seeking a Senior ML Infrastructure/MLOps Engineer to build and operate a model-serving platform. You will integrate machine learning models using PyTorch and TensorFlow, develop inference APIs, optimize performance, and deploy models using Docker and AWS.

• Build and operate a model-serving platform (e.g., Triton Inference Server). Integrate various model types and frameworks (e.g., PyTorch, TensorFlow). Develop inference APIs (batch and streaming). Design robust input and output schemas for ML models. Optimize performance (latency, throughput, GPU utilization). Containerize and deploy models using Docker and AWS.

• Strong Python skills (backend/ML runtime). Experience with ML inference and serving (e.g., Triton, TorchServe). Solid understanding of model inputs/outputs, batching vs streaming, FP32/FP16/quantization. Proficient with Docker and production deployments. Strong debugging skills in distributed ML systems. Basic knowledge of CUDA/GPU computing. Good German and English skills.