Role Overview
As a Senior Software Engineer for AI Model Serving at Speechify, based in Vitória, Brazil, you will design, implement, and maintain scalable inference services that power Speechify's AI-enabled reading features. You will collaborate with ML researchers and platform engineers to bring models from research to production with reliability and low latency.
Responsibilities
- Architect and implement backend services for model serving (Python, Go), REST and gRPC APIs, and data pipelines.
- Deploy, monitor, and optimize production ML models and inference workloads.
- Design and maintain scalable, containerized infrastructure using Kubernetes and Docker.
- Collaborate with ML researchers to understand model requirements and performance targets.
- Participate in code reviews, testing, and reliability improvements.
- Mentor junior engineers and promote best practices for software quality and security.
Qualifications
- 5+ years of software engineering experience.
- Experience with ML model serving systems (TensorFlow Serving, TorchServe, Triton) and distributed systems.
- Proficiency in Python; familiarity with Go/Java/Scala.
- Experience with Kubernetes, Docker, CI/CD, monitoring and tracing (Prometheus, OpenTelemetry).
- Cloud experience (AWS, GCP, or Azure).
- Strong problem-solving, communication, and collaboration skills.
Nice to Have
- Experience with Speechify's domain or text-to-speech/NLP.
- Knowledge of data privacy and security best practices.
What We Offer
- Competitive compensation; salaries are presented in thousands of USD.
- On-site role in Vitória with opportunities for hybrid arrangements.
- Collaborative, mission-driven environment focused on impactful AI technology.