Senior Software Engineer, AI Model serving - Sheffield, United Kingdom

Overview

Speechify is looking for a Senior Software Engineer, AI Model Serving to join our team in Sheffield, United Kingdom. In this role you will design, build, and operate scalable AI model serving infrastructure that powers Speechify's AI features. You will collaborate with data scientists, ML engineers, and platform teams to bring models from experimentation to production, ensuring reliability, low latency, and secure deployments.

Responsibilities

• Design, implement, and operate scalable AI model serving services and APIs.
• Optimize latency and throughput for inference workloads.
• Prototype and deploy new ML models into production environments.
• Build and maintain CI/CD pipelines for ML deployments.
• Collaborate with ML engineers to productionize models, monitoring, and alerting.
• Mentor junior engineers and contribute to software architecture decisions.
• Ensure security, reliability, and observability of serving infrastructure.

Qualifications

• 5+ years of software engineering experience with a strong backend focus.
• Proficiency in Python (or similar) and building scalable services.
• Experience with ML model serving frameworks (e.g., TensorFlow Serving, TorchServe, Triton) and ability to deploy on cloud platforms (AWS, GCP, Azure).
• Experience with containers (Docker), orchestration (Kubernetes), and CI/CD tooling.
• Strong problem solving, debugging, and communication skills.
• Ability to work in a collaborative, fast-paced environment.

Tech Stack

• Python
• TensorFlow / PyTorch
• TorchServe / TensorFlow Serving / Triton
• Kubernetes
• Docker
• AWS / GCP / Azure
• ML Ops concepts

About Speechify

Speechify is a leading Read Aloud application that helps people listen to content. We value collaboration, innovation, and a strong customer focus. Join us to build the next generation of AI-powered reading experiences.