ML Platform & Infrastructure Engineer

Build secure, high-performance systems that move physics models from research experiments into dependable services and customer environments.

• Develop scalable APIs and model inference services.
• Implement model packaging, versioning, deployment, and observability.
• Build scientific dataset access and discovery services.
• Optimize CPU/GPU inference performance.
• Support cloud, on-premises, customer-managed, and air-gapped deployment patterns.
• Implement authentication, authorization, logging, and monitoring.
• Build CI/CD, automated testing, and reliable releases.

• Strong software engineering in Python, Go, Rust, or C++.
• Experience operating distributed backend systems and APIs.
• Docker, Kubernetes, Linux, and cloud infrastructure.
• Familiarity with ML serving or GPU workloads.
• Infrastructure-as-code, observability, and security practices.

• Triton Inference Server or PyTorch model serving.
• AWS, GCP, Azure, GPU orchestration.
• MLOps, model registries, dataset management.
• Restricted or regulated deployment environments.

Move models into secure production with measurable reliability and inference performance.

Send your CV and a relevant paper, technical project, GitHub repository, or portfolio to careers@ratiolabs.ai. Suggested email subject: “Platform”.