[Akamai] Principal Software Engineer

The Akamai Inference Cloud team is part of Akamai's Cloud Technology Group. It builds AI platforms that support efficient, compliant, and high-performing AI inference applications, enabling customers to run inference models and developers to create advanced AI solutions.

• Broad software engineering experience with deep expertise in AI inference optimization, model serving, and large language model deployment at scale.
• Mastery of inference frameworks such as TensorRT, vLLM, TorchServe, and Triton.
• Experience in containerization strategies and hardware-specific optimizations for AI workloads.
• Expert-level proficiency with cloud-native technologies, Kubernetes, distributed systems, and designing services at global scale with strict SLOs.
• Proven experience in building platforms for AI developers, including retrieval-augmented generation (RAG), agents, and fine-tuning workflows.
• Excellent technical leadership, mentoring skills, and effective cross-team communication.
• Deep knowledge of AI safety, responsible AI practices, and explainability frameworks.

• Architect and design the core infrastructure of the Akamai Inference Cloud to ensure performance, compliance, economy, and explainability.
• Provide thought leadership on AI inference optimization, model serving architectures, and technical standards.
• Make critical technical decisions on frameworks, tools, and approaches for AI workload deployment and global traffic orchestration.
• Mentor engineers and collaborate with cross-functional teams to define technical requirements and enhance team capabilities.
• Contribute hands-on to critical path development, code reviews, and architectural implementations.