Senior Software Engineer, AI Model Serving – Speechify
Speechify is seeking a skilled Senior Software Engineer to design, build, and operate AI model serving infrastructure in Bishkek, Kyrgyzstan. This role focuses on delivering scalable, low-latency services for production ML models and collaborating with AI/ML teams to advance Speechify's capabilities.
Responsibilities
- Design, implement, and maintain scalable model serving APIs and infrastructure.
- Optimize latency, throughput, and reliability of ML model deployments.
- Collaborate with ML researchers to containerize, deploy, and monitor models in production.
- Build and maintain CI/CD pipelines, tests, and observability tooling.
- Ensure security, performance, and reliability of production services.
Requirements
- 5+ years of software engineering experience.
- Experience with ML model serving frameworks (e.g., TensorFlow Serving, TorchServe) or similar tooling.
- Proficiency in Python; additional languages (Go, Java, C++) are a plus.
- Experience with cloud platforms (AWS/GCP/Azure) and containerization (Docker, Kubernetes).
- Strong problem-solving, collaboration, and communication skills.
Nice to Have
- Experience with NLP, speech technologies, or related domains.
- Familiarity with Speechify or similar audio/text product ecosystems.
About Speechify: Speechify builds accessible reading and listening experiences by converting text to natural-sounding speech, enabling users to consume content efficiently across devices.