Trida AI is expanding its Forward Deployed Engineering bench for upcoming customer engagements. Engineers in this pool are first in line for client deployments as engagements start.

About the role: Trida AI deploys Forward Deployed Engineers inside enterprise customer teams to design, build, and ship production AI systems — agents, retrieval, and data integrations — and to leave behind systems the customer can operate themselves. Success is production adoption and measurable workflow impact, not a demo. Travel to customer sites up to 40% may be required depending on the engagement.

In this role you will:

• Design and ship LLM agents that plan and act across tools, APIs and enterprise data

Build high-performance retrieval: embeddings, vector search, memory and context pipelines

Build MCP servers, sub-agents and reusable agent skills for production workflows

Design human-in-the-loop review and approval steps into agentic workflows

Evaluate agent quality and reliability, fix failure modes with data

You may be a good fit if:

Production Python and shipped RAG/agentic applications (ReAct, plan-and-execute or equivalent)

Fluency across the LLM stack: frontier models, vector databases, orchestration frameworks

You think in systems: latency, cost, reliability and observability from the start

Must be authorized to work in the US; Trida AI does not provide sponsorship. Trida AI LLC is an equal opportunity employer. We welcome applicants of all backgrounds. If you need an accommodation in the application process, contact careers@trida.ai. Location: Remote — United States (Charlotte, NC base).