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

Overview

Speechify is seeking a Senior Software Engineer to join our AI Model Serving team in Liverpool, United Kingdom. You will design, implement, and operate scalable production-grade infrastructure to host and serve machine learning models for inference in Speechify products.

Responsibilities

• Design, implement, and maintain model-serving infrastructure and microservices for production ML models.
• Deploy models to production with versioning, feature flags, canary releases, and rollback strategies.
• Build robust APIs (REST and gRPC) and tooling to support model deployment, monitoring, and telemetry.
• Optimize latency, throughput, memory usage, and cost; implement autoscaling on Kubernetes.
• Instrument monitoring (Prometheus, Grafana, OpenTelemetry), logging, and alerting; troubleshoot production issues.
• Collaborate with ML researchers and data scientists to evaluate new models and integrate them into production.
• Mentor junior engineers, participate in code reviews, and contribute to architecture decisions.
• Ensure security, privacy, and compliance in data handling and access controls.

Qualifications

• 5+ years of software engineering experience; strong Python development skills.
• Hands-on experience deploying AI model serving frameworks (TorchServe, TensorFlow Serving, or Triton) and production ML deployment.
• Proficiency with Kubernetes, Docker, cloud platforms (AWS, GCP), and CI/CD pipelines.
• Experience building scalable distributed systems, asynchronous processing, and designing robust APIs (REST/gRPC).
• Familiarity with monitoring/observability tools (Prometheus, Grafana, OpenTelemetry) and incident response.
• Bachelor's degree in Computer Science or related field; advanced degree a plus.

Nice to have

• Experience with large language models, prompt engineering, and data pipelines; MLOps familiarity.
• Knowledge of data privacy and security best practices.

About Speechify

Speechify is a leading provider of AI-powered text-to-speech solutions that help people listen to content more efficiently. Join a collaborative, fast-paced team building products used worldwide.