AgentGraph pairs enterprises with vetted AI engineers to design and ship agents, MCP servers, and agentic systems. Builders join the network and are matched to client engagements that fit their expertise and working style.
Applied AI Engineers are the builders who put agentic systems into production. You work on well-defined use cases, in the client's core codebase, shipping regularly — this is a technical, customer-facing role where the measure of the work is what runs.
What you will do
- Push code to client core codebases regularly, following the client's own review, testing, and release process rather than working off to one side
- Build the systems the use case calls for: agents and multi-step workflows, MCP servers, retrieval pipelines, structured extraction, and the integrations that connect them to real business systems
- Work directly with client engineers and stakeholders on well-defined use cases, translating a scoped problem into a shipped, maintained implementation
- Own delivery end to end — design, implementation, testing, rollout, and the debugging that follows a real user finding the edge you missed
- Instrument what you ship: evaluation suites, tracing, cost and latency accounting, and the monitoring that catches quality drift before the customer does
How this differs from Forward Deployed Engineer
This role overlaps substantially with the Forward Deployed Engineer skill set — both are technical and both are customer-facing — but it emphasizes building. Where a Forward Deployed Engineer decides what to build and why, you take a well-defined use case and make it real. Many builders in our network move between the two depending on the engagement.
What we look for
- A track record of shipping production software into codebases you did not write, at a pace a client can feel
- Depth in the agentic stack: agent frameworks, MCP, retrieval, structured output, evaluation, and the operational side of running LLM features in production
- Comfort being customer-facing as an engineer — able to explain a tradeoff to a non-technical stakeholder without flattening it
- Judgment about when the simple approach beats the interesting one
How engagements work
You join the AgentGraph network as an independent contractor rather than an employee. We match you to client engagements based on your expertise, availability, and the shape of the work; scope, rate, and expected commitment are agreed before an engagement starts. Work is remote, and engagements range from short scoped projects to sustained embedded work with a single client.
Compensation
Rates are set per engagement, based on scope, depth of expertise, and expected commitment. We are transparent about the rate before you accept any engagement.