This is a fully remote position, open to applicants in China.

📋 Description

• Create clear and well-documented examples and projects for the developer community.

• Design and document distributed systems intended for global scalability and high-performance edge inference.

• Produce written and video materials, including in-depth YouTube tutorials and concise social media videos.

• Enhance and demonstrate LLM inference on GPUs, concentrating on performance, latency, and efficiency within the open-source environment.

• Spearhead community-building initiatives across GitHub, Discord, and various industry events.

• Offer actionable insights to engineering teams derived from hands-on testing and feedback from the developer community.

• Represent Akamai through technical storytelling at conferences, workshops, live-coding sessions, and engagements with the developer community both in Asia and worldwide.

• Work collaboratively with engineering and product teams to showcase Akamai's technological capabilities and champion the global AI developer ecosystem.

⛳️ Requirements

• Extensive experience in AI Engineering, LLMs, and the open-source AI ecosystem.

• Practical experience with AI frameworks such as PyTorch, Hugging Face Transformers, vLLM, LangChain, LlamaIndex, Crew AI, Pydandic AI, or similar technologies.

• Expertise in running and optimizing GPU inference.

• Experience in deploying models within edge computing environments.

• Knowledge of constructing and scaling distributed systems for global workloads.

• Proficiency in producing high-quality video content and clear technical documentation.

• Capability to identify emerging AI trends and convert them into useful developer resources.

• Ability to mentor developers and influence technical roadmaps across cross-functional teams.