Principal Software Engineer - Akamai Inference Cloud

Technologies we use

About the project

Your responsibilities

• Architecting and designing the core infrastructure of Akamai Inference Cloud, ensuring it is performant, compliant, economical, and explainable.
• Providing thought leadership on AI inference optimization, model serving architectures, and establishing technical standards for the platform.
• Making critical technical decisions on frameworks, tools, and approaches for AI workload deployment and global traffic orchestration.
• Mentoring engineers and collaborating with cross-functional teams to define technical requirements and elevate team capabilities.
• Contributing hands-on to critical path development, code reviews, and architectural implementations.

Our requirements

• Have broad software engineering experience with deep expertise in AI inference optimization, model serving, and LLM deployment at scale.
• Demonstrate mastery of inference frameworks (TensorRT, vLLM, TorchServe, Triton), containerization strategies, and hardware-specific optimizations for AI workloads.
• Show expert-level proficiency with cloud-native technologies, Kubernetes, distributed systems, and architecting services at global scale with strict SLOs.
• Possess strong opinions and proven experience building platforms for AI developers (RAG, agents, fine-tuning workflows).
• Demonstrate excellent technical leadership with ability to mentor engineers, influence architectural decisions, and communicate effectively across teams.
• Have deep knowledge of AI safety, responsible AI practices, and explainability frameworks.

Benefits

Work in a way that works for you

Working for you

Join Our International Tax Team!