Senior II AI Inference Platform Lead

Akamai Technologies, Inc.; Lansing (MI); On-site; USD 146,000 - 264,000; Full time

Job summary

Akamai Technologies, Inc. is seeking a Senior II Software Engineer Lead to drive the design and delivery of our AI inference platform, delivering OpenAI-compatible endpoints and scalable inference workloads across regions.

You will mentor engineers, make architecture choices, and champion modern DevOps practices, containerization with Kubernetes and Docker, and CI/CD pipelines to ensure reliable, high-performance operations in a distributed cloud environment.

Qualifications

• 8 years of relevant experience and a Bachelor's degree or its equivalent.
• Solid proficiency in distributed systems, cloud services, and platform engineering.
• Hands-on experience with AI inference, model serving, or LLM deployment and inference frameworks (TensorRT, vLLM, TorchServe, Triton).
• Expertise in containerization and orchestration technologies including Kubernetes and Docker.
• Experience building scalable, high-performance systems with CI/CD and infrastructure-as-code.
• Demonstrated technical leadership through mentoring and code-quality advocacy.

Responsibilities

• Leading the design and implementation of critical platform components for Akamai Inference Cloud, ensuring performance, scalability, and reliability
• Driving technical decisions for AI inference workloads and domain tooling.
• Mentoring engineers through code reviews and design discussions.
• Implementing and optimizing containerized AI workloads with hardware-specific optimizations.
• Collaborating across teams to define technical requirements and ensure operational excellence.

Skills

Leadership

Mentoring

Code Reviews

Education

Bachelor's degree or equivalent

Tools

TensorRT

vLLM

TorchServe

Triton

Kubernetes

Docker

REST/gRPC APIs

CI/CD

Infrastructure as Code

Job description

Akamai Technologies, Inc. is seeking a Senior II Software Engineer Lead to drive the design and delivery of our AI inference platform, delivering OpenAI-compatible endpoints and scalable inference workloads across regions.

You will mentor engineers, make architecture choices, and champion modern DevOps practices, containerization with Kubernetes and Docker, and CI/CD pipelines to ensure reliable, high-performance operations in a distributed cloud environment.