Senior Software Engineer

Location Details: Remote, India This is a remote position, so you’ll be working remotely from your home. You may occasionally visit a GoDaddy office to meet with your team for events or meetings. Join Our team The ML Engineering (MLE) team builds and operates the production infrastructure that brings ML models to life across GoDaddy's global markets. We own model serving infrastructure, CI/CD pipelines for model deployment, the Model Gateway, API design, observability, and all inference context infrastructure. We partner with ML scientists who build the models — our job is to design the systems and make those models reliable, scalable, and observable in production. We are looking for a Senior Software Development Engineer to join our India-based engineering team. This is a mid-level IC role focused on building and operating ML infrastructure — writing production code, building deployment pipelines, improving observability, and partnering with ML scientists to productionize models! You'll work closely with the India-based engineering manager and collaborate daily with engineers in North America and India. What you'll get to do... • Build and maintain model serving infrastructure — deploying ML models to production endpoints, managing autoscaling, and ensuring low-latency inference • Develop and improve CI/CD pipelines for model training, testing, deployment, and promotion across environments • Write production services in Python and Go, with infrastructure-as-code in TypeScript (CDK). Partner with ML scientists to translate trained models into production-grade, monitored, and maintainable services • Build and maintain online feature stores, inference context APIs, and data pipelines that feed production models • Instrument services for observability — metrics, logging, tracing, alerting — and participate in on-call rotation. Contribute to the Model Gateway for experimentation, traffic routing, and fallback logic • Debug production issues, investigate performance regressions, and drive root-cause analysis. Collaborate daily with engineers, scientists, data engineers, and product teams across time zones Your experience should include... • 3–5 years of software development experience shipping production applications • Proficiency in Python; working knowledge of Go or TypeScript is a plus • Experience with AWS services (ECS/EKS, Lambda, DynamoDB, S3, or equivalents) • Solid understanding of microservices, REST APIs, and distributed systems fundamentals • Experience building or maintaining CI/CD pipelines (GitHub Actions, Jenkins, or similar) • Experience with containerization (Docker) and orchestration basics (Kubernetes or ECS) • Strong communication skills — ability to collaborate across time zones with engineers and scientists • Ownership mindset — willingness to take end-to-end responsibility for features from design through production You might also have... • Experience with ML model serving frameworks (SageMaker, vLLM, TorchServe, Triton) • Familiarity with observability tools (OpenTelemetry, Prometheus, Grafana, CloudWatch) • Experience with infrastructure as code (CDK, CloudFormation, Terraform) • Exposure to ML concepts — model training, inference, feature engineering, drift detection • Experience with AI-assisted development tools • Bachelor's or Master's degree in Computer Science, Engineering, or equivalent experience We encourage you to apply even if your experience or skillset doesn’t align perfectly with every requirement. We value a wide range of backgrounds and transferable skills, and we are excited to support learning and growth. We've got your back...    We offer a range of total rewards that may include paid time off, retirement savings (e.g., 401k, pension schemes), bonus/incentive eli