AI / LLM Developer Needed – In-Person Project (South Florida)
On-site
Core
Designing and implementing a locally hosted AI assistant running on high-performance hardware for private, long-term use.
Role type
hands-on IC AI/LLM developer
Builds
local or hybrid LLM stack with persistent memory and knowledge storage
Domain
consumer AI / local inference
Deliverable
production ML models
Required skills
LLM deployment, Python, local inference optimization, vector databases, embeddings, agent frameworks, hardware configuration
Preferred skills
none stated
Technologies
Ollama, LM Studio, llama.cpp, LangChain, vector databases
Responsibilities
Deploying and configuring 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
Seniority
mid-level IC

