Senior Software Engineer, AI Model serving - Incheon, South Korea

Overview

Speechify is seeking a Senior Software Engineer, AI Model Serving to join our AI Platform team in Incheon, South Korea. You will design, build, and operate scalable model serving systems powering Speechify's AI features. You will collaborate with ML researchers and software engineers to deploy production models, ensure low latency, reliability, and observability, and help advance ML Operations tooling, versioning, and monitoring.

Responsibilities

• Design, implement, and maintain scalable AI model serving infrastructure and APIs (inference services, gRPC/REST).
• Collaborate with ML researchers and engineers to deploy production models and optimize performance.
• Improve latency, throughput, reliability, monitoring, and observability of online inference systems.
• Build and maintain CI/CD pipelines for ML models and related tooling; contribute to model versioning and experimentation workflows.
• Instrument services with robust logging, tracing, and alerting; troubleshoot production issues and improve system reliability.
• Mentor and guide junior engineers; contribute to code quality and documentation.

Requirements

• 3+ years of software engineering experience, with backend or ML infrastructure focus.
• Hands-on experience with model serving frameworks (TensorFlow Serving, TorchServe, or custom serving solutions).
• Proficiency in Python and at least one systems language (Go, C++, Rust).
• Experience with Kubernetes and cloud platforms (AWS, GCP, or Azure).
• Familiarity with ML Ops concepts, data pipelines, monitoring, and observability.
• Strong problem-solving abilities and collaboration skills.
• Bachelor’s degree in Computer Science or related field (or equivalent practical experience).

About Speechify

Speechify is a leader in AI-powered reading and learning tools, delivering fast, reliable, and scalable experiences to users worldwide.