Role overview
Speechify is seeking a Senior Software Engineer to join our AI Model Serving team in Natal, Brazil. You will design, implement, and scale production-grade model serving infrastructure for real-time AI features across Speechify products.
Responsibilities
- Design, implement, and maintain scalable model serving systems for real-time AI inference.
- Collaborate with ML researchers to deploy, monitor, and.optimize models.
- Build robust APIs, data pipelines, and microservices to support AI features.
- Ensure low latency, high availability, and reliability of inference workloads.
- Write clean code, perform rigorous testing, and participate in code reviews.
- Contribute to CI/CD pipelines and orchestration (Docker, Kubernetes).
- Help with on-call rotations and incident response.
Requirements
- 5+ years of software engineering experience.
- Strong experience with model serving frameworks (e.g., TensorFlow Serving, TorchServe) and ML inference.
- Proficiency in Python; experience with Go or Java is a plus.
- Experience with distributed systems, APIs (REST/gRPC), and cloud platforms (AWS/GCP/Azure).
- Familiarity with Docker and Kubernetes; experience with CI/CD.
- Strong problem-solving and collaboration skills, ability to work with cross-functional teams.
- Bachelor's degree in CS or related field or equivalent experience.
Nice to have
- Experience with ML workflows, feature stores, monitoring of ML models in production.
- Proficiency in Portuguese is a plus for local collaboration.
About Speechify
Speechify builds AI-powered tools to enhance reading and comprehension through advanced ML techniques. This role offers the chance to impact a broad user base by delivering scalable AI model serving capabilities from our Natal office.