Overview
Speechify is seeking a Senior Software Engineer to join our AI model serving team in Busan, South Korea. In this production-focused role, you will design and implement scalable, low-latency inference services that run Speechify's machine learning models in production. You will collaborate with ML researchers and data scientists to productionize models, optimize performance, and ensure reliability and observability of model-serving systems. This is a hands-on software engineering role focused on building robust model-serving APIs and integrating with cloud infrastructure.
Responsibilities
- Design, implement, and operate scalable AI model serving infrastructure for production workloads.
- Build low-latency inference services and APIs using Python/C++.
- Collaborate with ML researchers to productionize new models and ensure accuracy and reliability.
- Optimize model serving performance, memory usage, and latency; implement monitoring, logging, and alerting.
- Build and maintain CI/CD pipelines for ML workloads; contribute to testing and quality.
- Mentor junior engineers; participate in code reviews and architecture decisions.
- Collaborate with product and platform teams to define requirements and deliver features.
Qualifications
- 5+ years of software engineering experience.
- Strong proficiency in Python and/or C++.
- Experience with ML model serving frameworks (TorchServe, TensorFlow Serving, Triton) or similar.
- Experience with Kubernetes, Docker, and cloud platforms (AWS, GCP, Azure).
- Familiarity with RESTful APIs, gRPC, and building scalable microservices.
- Excellent debugging, performance optimization, and problem-solving skills.
- Bachelor’s degree in Computer Science, Engineering, or related field; Master’s preferred.
Nice to have
- Experience with ML frameworks such as PyTorch, TensorFlow.
- Experience with monitoring and observability (Prometheus, Grafana).
- Knowledge of data pipelines and ML workflow tools.
About Speechify
Speechify is a leading AI-powered text-to-speech platform that enables people to consume written content hands-free, enhancing learning and productivity.
What we offer
- Competitive salary and benefits.
- Collaborative, fast-paced work environment.