Senior Software Engineer, AI Model Serving - San Sebastián, Spain

Senior Software Engineer, AI Model Serving – Speechify (San Sebastián, Spain)

Join Speechify as a Senior Software Engineer focused on AI model serving. You will design, implement, and scale the infrastructure that hosts AI models in production, collaborating with ML researchers and product teams to deliver fast, reliable AI experiences to users in Spain and beyond.

Role Overview

In this on-site role based in San Sebastián, you will own the end-to-end lifecycle of AI model serving systems, from API design to deployment, scalability, monitoring, and continuous improvement.

What you'll do

• Design, implement, and scale AI model serving infrastructure and APIs with low latency and high availability
• Collaborate with ML researchers to deploy models and improve serving performance
• Build and maintain containerized services using Docker and Kubernetes
• Develop robust CI/CD pipelines for model deployment and iteration
• Monitor, profile, and optimize latency, throughput, and reliability
• Contribute to architecture decisions and mentor junior engineers

Qualifications

• 5+ years of professional software engineering experience
• Strong Python skills and experience with ML model serving frameworks
• Experience with Docker, Kubernetes, and cloud platforms (AWS/GCP/Azure)
• Experience building scalable distributed systems and APIs (REST/gRPC)
• Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field

Nice to Have

• Experience with TorchServe, TensorFlow Serving, ONNX, or FastAPI
• Familiarity with monitoring/observability tools and ML model governance

Location

San Sebastián, Spain (on-site)

Compensation

Salary is not disclosed. Speechify offers a competitive compensation and benefits package.

How to apply

Apply through the Greenhouse posting: https://job-boards.greenhouse.io/speechify/jobs/5614376004