I’m seeking an experienced AI / LLM developer based in Florida for a paid, contract-based project that involves in-person collaboration.
This role is suited to someone with strong hands-on experience designing and running local or hybrid LLM systems on high-performance hardware.
The project involves designing and implementing a locally hosted AI assistant running on a high-powered laptop for private, long-term use.
Key components include:
Deploying and configuring a local or hybrid LLM stack
Optimizing performance across CPU, GPU, RAM, and VRAM
Designing a persistent memory and knowledge storage system
Developing methods to retain and reuse structured knowledge and user context in a compliant and technically sound way
Building the system with extensibility and future customization in mind
This is a hands-on engineering role, not prompt engineering or theoretical research.
Demonstrated experience working with LLMs (local or hybrid)
Strong Python proficiency
Familiarity with tools such as Ollama, LM Studio, llama.cpp, LangChain, vector databases, embeddings, or agent frameworks
Experience with local inference, persistence, and memory systems
Comfortable configuring and optimizing high-performance local hardware
Ability to clearly explain technical trade-offs and limitations
Location: Florida (in-person collaboration required)
Engagement: Paid, contract / project-based
Compensation: Competitive, based on experience
Confidentiality agreement required
If this aligns with your background, please message me with:
A brief summary of relevant experience
Examples of similar projects
A high-level outline of how you would approach this build