Developed and delivered the Hugging Face LLM provider integration for the Kong/kong repository, enabling Kong’s LLM driver to interface directly with Hugging Face’s inference API for both serverless and dedicated LLM instances. The work involved implementing a new provider driver in Lua, designing a provider-specific schema, and building request and response transformations to normalize data between Kong and Hugging Face endpoints. This integration expanded deployment options for Kong users, allowing seamless LLM workloads backed by Hugging Face. The solution focused on backend development and API integration, with changes tracked through a dedicated commit to ensure traceability and facilitate code review.