GenAI Engineer: Document Intelligence & Multimodal Generation

MaintainX; Raleigh (NC); On-site; USD 120,000 - 180,000; Full time

Benefits offered by this job

Competitive salary

Equity opportunities

Healthcare

401(k)

Take what you need PTO

Job summary

MaintainX is seeking a GenAI-focused engineer to own the Generation half of Document Intelligence, turning multimodal primitives into schema-valid entities while upholding strict quality standards.

You will design prompts, define schemas and validators, and build eval datasets. You will work with video, PDF, audio, and images converted to text or structured output, guiding model choices to balance quality, cost, and latency.

Qualifications

• Strong applied GenAI craft: prompt engineering, structured output / tool-use, RAG and retrieval-context patterns.
• Real eval discipline: built datasets and rubrics, measured factuality/relevance/quality, closed the loop on regressions.
• Shipped LLM features into production services, not notebooks, and can connect model performance to product impact.
• Comfort working with multimodal inputs - video, PDF, audio, image - converted to text or structured output.

Responsibilities

• Design and iterate recipe prompts — system, few-shot, and context assembly — for each generation recipe.
• Define per-entity target schemas and domain validators (procedure step-type rules, field caps) that generated output has to pass.
• Build generation-quality eval datasets and rubrics, offline and online, running on LLMX's eval pipeline, and close the loop when quality regresses.
• Assemble multimodal context windows from keyframes, transcript, and OCR so each model call has exactly what it needs.
• Choose the model and token budget per recipe based on quality, cost, and latency tradeoffs.

Skills

Prompt engineering

Structured output

RAG patterns

Multimodal input

Production ML features

Tools

OCR

Retrieval systems

Fine-tuning

Job description

MaintainX is seeking a GenAI-focused engineer to own the Generation half of Document Intelligence, turning multimodal primitives into schema-valid entities while upholding strict quality standards.

You will design prompts, define schemas and validators, and build eval datasets. You will work with video, PDF, audio, and images converted to text or structured output, guiding model choices to balance quality, cost, and latency.