Senior Software Engineer, AI Model Serving - Sydney, Australia

About Speechify

Speechify is a leading AI-powered text-to-speech platform delivering fast, natural-sounding voices. This role is based in Sydney, Australia.

Role Overview

As a Senior Software Engineer, AI Model Serving, you will design and implement scalable services to host and serve machine learning models that power Speechify’s real-time features. You will collaborate with ML researchers, data scientists, and platform teams to ensure low latency, high reliability, and robust monitoring in production.

Responsibilities

• Build and maintain scalable model-serving infrastructure (APIs, gRPC/REST endpoints)
• Own deployment pipelines, model versioning, A/B testing, and feature flags
• Instrument monitoring, alerting, tracing, and incident response
• Collaborate with ML researchers to optimize models for serving performance
• Mentor junior engineers and contribute to design reviews

Requirements

• 5+ years of software engineering experience
• Strong Python development (or equivalent) and APIs
• Hands-on experience with ML model serving frameworks (TensorFlow Serving, TorchServe, ONNX)
• Experience with distributed systems, containerization (Docker, Kubernetes)
• Cloud experience (AWS or GCP), CI/CD, and monitoring tooling
• Excellent collaboration and communication skills

Nice-to-have

• Experience with Rust or Go
• Experience with low-latency systems and ML infrastructure

What we offer

Competitive compensation, health benefits, and opportunities to impact a growing product used by thousands of users daily. This role is based in Sydney and supports a collaborative, inclusive, and fast-paced environment.