About Speechify
Speechify is a leading AI-powered reading platform that helps people listen to content anywhere. We are seeking a Senior Software Engineer to join our AI Model Serving team in Salvador, Brazil, to help deploy and scale machine learning models in production.
Role overview
As a Senior Software Engineer, AI Model Serving, you will design, build, and maintain scalable infrastructure and APIs to serve ML models with low latency. You will collaborate closely with ML researchers and data teams to deploy models, monitor performance, and ensure reliability in production.
Responsibilities
- Design, implement, and maintain scalable model-serving infrastructure and APIs for real-time inference
- Collaborate with ML researchers to deploy models to production and monitor performance
- Build robust CI/CD pipelines, automated tests, and observability tooling
- Optimize latency, throughput, and resource usage; implement model versioning and rollback strategies
- Ensure security, reliability, and compliance in production systems
- Mentor junior engineers and participate in code reviews
Requirements
- 5+ years of software engineering experience
- Strong Python proficiency; experience with ML model deployment and serving frameworks (TorchServe, TensorFlow Serving, or custom)
- Experience with Docker, Kubernetes, and cloud platforms (AWS/GCP/Azure)
- Familiarity with REST/gRPC, microservices, and CI/CD tooling
- Good communication skills and ability to work across teams
- Bachelors or Master’s in Computer Science or related field
Nice-to-have
- Experience with Portuguese language or Brazilian teams
- Experience with MLOps tooling and monitoring (Prometheus, Grafana)
Benefits
- Competitive salary and equity
- Health insurance and wellness benefits
- Flexible work schedule; opportunities for growth and learning
- Collaborative, inclusive remote-friendly environment
How to apply
Apply via the Greenhouse listing: Speechify – Senior Software Engineer, AI Model Serving