GenAI Engineer, Document Intelligence - Quality Gen

MaintainX; Boston (MA); On-site; USD 150,000 - 190,000; Full time

Job summary

MaintainX is seeking a Role in Document Intelligence to own the Generation half of Document Intelligence, turning multimodal primitives into schema-valid entities while enforcing strict quality controls.

You will design prompts, define schemas and validators, build eval datasets, and assemble multimodal context for each model call. The role emphasizes production-ready GenAI features, with a focus on accuracy and reliability across video, PDF, audio, and images.

Qualifications

• Proven experience designing prompts and structured outputs for LLMs.
• Ability to build eval datasets and rubrics to measure quality.
• Experience shipping LLM features into production services.
• Comfort processing multimodal inputs (video, PDF, audio, image) and converting to text or structured data.

Responsibilities

• Design and iterate recipe prompts for each generation recipe.
• Define per-entity target schemas and validators that generated output must pass.
• Build generation-quality eval datasets and rubrics for offline and online use.
• Assemble multimodal context windows from keyframes, transcripts, and OCR for model calls.
• Choose the model and token budget per recipe balancing quality, cost, and latency.

Skills

GenAI prompts

Evaluation discipline

Production LLM features

Multimodal inputs handling

Job description

MaintainX is seeking a Role in Document Intelligence to own the Generation half of Document Intelligence, turning multimodal primitives into schema-valid entities while enforcing strict quality controls.

You will design prompts, define schemas and validators, build eval datasets, and assemble multimodal context for each model call. The role emphasizes production-ready GenAI features, with a focus on accuracy and reliability across video, PDF, audio, and images.