Seeking proposals: AI / LLM Developer (South Florida – In-Person Required)

I am looking to engage an experienced AI / LLM developer who is physically based in South Florida (Palm Beach, Broward, or Miami-Dade). This is a paid, project-based engagement that requires in-person collaboration. Remote candidates will not be considered.

The objective is to design and implement a locally hosted AI system running on a high-powered laptop, functioning as a private, personalized AI assistant.

The project will include:

Deploying a local or hybrid LLM architecture

Optimizing the system to fully utilize available hardware (CPU, GPU, RAM, VRAM)

Designing a persistent memory and knowledge system

Architecting an approach to mirror or preserve the accumulated knowledge, context, and behavioral patterns of an existing ChatGPT account, within technical and platform constraints

Building the system for long-term use, extensibility, and customization

This is not a beginner role, not prompt engineering, and not a theoretical exercise. I’m looking for someone who understands both the capabilities and limits of current AI tooling and can engineer a practical, robust solution.

Strong hands-on experience with LLMs (local or hybrid)

Python proficiency (required)

Familiarity with tools such as Ollama, LM Studio, llama.cpp, LangChain, vector databases, embeddings, fine-tuning, or agent frameworks

Experience with local inference, memory systems, and persistence

Comfortable configuring and optimizing high-performance local hardware

Ability to explain technical trade-offs clearly and realistically

Location: South Florida (in-person required)

Engagement: Paid, project-based / contract

Compensation: Competitive, based on experience

NDA required

If this aligns with your background, please DM me with:

A brief summary of your experience

Relevant projects or examples

A short outline of how you would approach this project