Senior Software Engineer, AI Model serving - Hanover, Germany

Senior Software Engineer, AI Model Serving – Speechify (Hanover, Germany)

Speechify is seeking a Senior Software Engineer to join our AI Model Serving team in Hanover, Germany. You will design, build, and operate scalable AI model serving infrastructure to deliver low-latency inference for production features powering our reading and text-to-speech experiences. You’ll collaborate with data scientists, ML engineers, and product teams to deploy models, optimize performance, monitor endpoints, and ensure reliability and security in production systems.

Overview

This on-site role is based in Hanover, Germany. You will drive the end-to-end lifecycle of AI models in production, from inference APIs to monitoring and reliability.

Responsibilities

• Design, implement, and operate scalable AI model serving components for production use
• Build and maintain APIs and services for model inference
• Deploy models to production using Docker/Kubernetes and cloud platforms (AWS, GCP, Azure)
• Monitor performance, latency, reliability, and observability; implement dashboards and alerts
• Collaborate with ML scientists to productionize models and optimize inference
• Improve CI/CD pipelines and test coverage
• Participate in architecture discussions and code reviews
• Mentor junior engineers and contribute to engineering best practices

Requirements

• 5+ years of software engineering experience
• Strong Python skills; experience with ML frameworks (TensorFlow, PyTorch)
• Experience with model serving frameworks (TensorFlow Serving, TorchServe, ONNX Runtime)
• Hands-on experience with Docker, Kubernetes, and cloud platforms (AWS, GCP, Azure)
• Familiarity with RESTful APIs, microservices, and scalable architectures
• Excellent problem-solving and collaboration skills
• Bachelor’s degree in Computer Science or related field (Master preferred)

About Speechify

Speechify is a leading provider of AI-powered reading and text-to-speech solutions designed to help people absorb information more efficiently. We’re building scalable, production-grade software that brings advanced ML capabilities to millions of users.

Location

Hanover, Germany