Remote AI Development & Support Engineer - Local LLMs & MCP

Starfish Storage Corporation; United States; Hybrid; USD 140,000 - 190,000; Full time

Job summary

Starfish Storage manages petabytes of unstructured data for national labs, research institutions, fintech, and pharma, and is building an AI-native layer with MCP servers, agentic workflows, and local LLM deployments. Researchers and engineers will interact with storage infrastructure through tools that enable autonomous data actions and governance.

In this role you will develop MCP servers, deploy and tune local LLMs, create production-grade agents for real customers, and run in constrained

Qualifications

• Solid grasp of agent architectures, prompt engineering, and MCP or tool-use patterns.
• Hands-on experience with local/open-source LLMs: you've run them, tuned them, deployed them.
• Comfortable working in Linux environments and debugging at the command line.
• Strong communicator: you can explain what's broken and why to both engineers and non-engineers.
• This is not a role for someone who has tried out some youtube tutorial videos on their own. You need to have some real experience implementing this.

Responsibilities

• Build and expand MCP servers that expose Starfish's data management capabilities to LLM-powered workflows.
• Develop intelligent agents that can reason over storage metadata at scale — including local LLM deployment and configuration using vLLM, Ollama, or similar.
• Create workflow automation and chat-based interfaces for querying and acting on Starfish data.
• Build proof-of-concept implementations and turn them into production-grade features.
• Support customers through installation, configuration, and troubleshooting of AI features and integrations.
• Get on calls with technical teams, understand their use cases, and translate requirements into working agents.

Skills

Agent architectures

Prompt engineering

Local/open-source LLMs

Linux

Command-line debugging

Python development

RAG pipelines

REST APIs

Docker

Storage systems / HPC

Communication with engineers

Tools

vLLM

Ollama

Vector databases

Job description

Starfish Storage manages petabytes of unstructured data for national labs, research institutions, fintech, and pharma, and is building an AI-native layer with MCP servers, agentic workflows, and local LLM deployments. Researchers and engineers will interact with storage infrastructure through tools that enable autonomous data actions and governance.

In this role you will develop MCP servers, deploy and tune local LLMs, create production-grade agents for real customers, and run in constrained