Job Description
Speechify is seeking a Senior Software Engineer, AI Model Serving to join our team in Belo Horizonte, Brazil. You will design, build, and scale the AI model serving infrastructure powering Speechify’s real-time features.
Responsibilities
- Design, implement, and maintain scalable AI model serving infrastructure for low-latency inference.
- Build robust APIs and services (REST and gRPC) to expose model predictions.
- Collaborate with ML researchers and software engineers to deploy and monitor models in production.
- Optimize latency, throughput, and resource usage; conduct performance profiling and capacity planning.
- Instrument systems with monitoring, logging, and alerting; write tests and documentation.
- Contribute to architecture decisions and participate in code reviews; mentor junior engineers.
Requirements
- Experience building production-grade ML model serving systems.
- Strong programming skills (Python is preferred; other languages such as Go or Java are a plus).
- Familiarity with ML frameworks (TensorFlow, PyTorch) and model packaging/versioning.
- Experience with containerization and orchestration (Docker, Kubernetes).
- Experience with cloud platforms (AWS, GCP, or Azure).
- Proven ability to design scalable, robust systems and troubleshoot complex issues.
- Excellent collaboration and communication skills; ability to work in a fast-paced team.
About Speechify
Speechify is a leading AI-powered reading tool that helps people listen to text, increasing productivity and accessibility. We’re building a diverse, collaborative team focused on delivering high-quality reading experiences.
Location
Belo Horizonte, Brazil
Why Join Us
Join a mission-driven team, grow your career, and work on impactful AI features in a supportive environment.