Overview
Speechify is seeking a Senior Software Engineer to join our AI Model Serving team in Recife, Brazil. You will design, build, and scale production-grade AI model serving infrastructure and APIs to support speech and text processing.
Responsibilities
- Design, implement, and maintain scalable AI model serving systems and APIs.
- Deploy ML models to production with monitoring, alerting, and tracing.
- Develop and optimize inference pipelines using TensorFlow Serving, PyTorch Serve, and related frameworks.
- Build and operate microservices using Docker and Kubernetes on AWS/GCP; contribute to CI/CD pipelines.
- Collaborate with ML engineers and data scientists to deliver reliable features and performance improvements.
- Mentor junior engineers and participate in code reviews to improve software quality.
Requirements
- 5+ years of software engineering experience with a focus on ML model serving.
- Strong proficiency in Python; Go experience is a plus.
- Hands-on experience with ML serving frameworks (TensorFlow Serving, PyTorch Serve, ONNX Runtime).
- Experience with Kubernetes, Docker, and cloud environments (AWS, GCP).
- Familiarity with monitoring/observability tools (Prometheus, Grafana, OpenTelemetry) and CI/CD practices.
- Excellent problem-solving and collaboration skills; ability to operate in a fast-paced startup environment.
Nice to have
- Experience with Nvidia GPUs and ML hardware acceleration.
- Experience with distributed systems, service mesh, or data pipelines.
Location: Recife, Brazil. On-site.