Senior Software Engineer, AI Model serving - Niterói, Brazil

Senior Software Engineer, AI Model Serving - Speechify

Location: Niterói, Brazil (On-site)

About Speechify

Speechify is a technology company focused on AI-powered reading and text-to-speech solutions. We build scalable software that makes content accessible through advanced AI models.

Role

As a Senior Software Engineer in AI Model Serving, you will design, develop, and operate production-grade AI model serving infrastructure, enabling low-latency inference for Speechify's AI models.

Responsibilities

• Design, develop, and maintain production-grade AI model serving infrastructure and services.
• Build scalable microservices to serve machine learning models with low latency and high reliability.
• Collaborate with data scientists and ML researchers to deploy research into production.
• Implement monitoring, logging, tracing, and alerting; ensure observability and reliability in production systems.
• Optimize performance and costs; participate in CI/CD and infrastructure automation.
• Mentor junior engineers and participate in code reviews and architectural discussions.

Qualifications

• 5+ years of professional software engineering experience.
• Strong programming experience in Python.
• Experience deploying and maintaining machine learning models in production.
• Proficiency with cloud platforms (e.g., AWS), containerization (Docker), and orchestration (Kubernetes).
• Experience with ML frameworks (PyTorch, TensorFlow) and model serving tools (TorchServe, MLflow).
• Experience with gRPC or REST APIs and building scalable distributed systems.
• Excellent communication and collaboration skills.

Nice to have

• Experience with MLOps, monitoring, and observability tooling.
• Portuguese language skills are a plus but not required.

How to apply

Please submit your application via Speechify's Greenhouse listing: https://job-boards.greenhouse.io/speechify/jobs/5616970004.