Applied AI Engineer

About the Company

MaintainX is the world's leading AI-powered maintenance and asset management platform, serving 14,000+ customers including Duracell, Shell, Cintas, and Brenntag. The company has raised $254M in funding, including a $150M Series D led by Bessemer Venture Partners and Bain Capital Ventures, and was named to the Forbes 2025 Cloud 100. MaintainX manages 13.9M+ assets, 79.5M+ completed work orders, and supports 150,000+ technicians generating trustworthy operating data weekly. Document Intelligence is the horizontal engine that transforms raw customer files into structured, AI-native maintenance knowledge.

About the Role

You'll own the Generation half of Document Intelligence: turning multimodal primitives (keyframes, transcripts, OCR) into schema-valid entities like SOPs while ensuring quality so "fast" never becomes "fast and wrong." You will work closely with the Processing side of Document Intelligence and report to the Engineering Lead.

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 must pass
• Build generation-quality eval datasets and rubrics, both offline and online, using LLMX's eval pipeline, and close the loop when quality regresses
• Assemble multimodal context windows from keyframes, transcript, and OCR to ensure each model call has exactly what it needs
• Choose the model and token budget per recipe based on quality, cost, and latency tradeoffs
• Leverage LLMX for model access and Attachments for ingestion, then hand off validated entities to the domains that own them

Requirements

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

Nice to Have

• LLM observability or cost awareness, or experience with an eval platform
• Document, PDF, or video understanding; OCR; retrieval systems
• Light fine-tuning experience or familiarity with the industrial/maintenance domain

Benefits

• Competitive salary and meaningful equity opportunities
• Healthcare, dental, and vision coverage
• 401(k) / RRSP enrollment program
• Take-what-you-need PTO

Work Culture

You’ll work alongside a global team that reflects MaintainX values: Smart Humble Optimists. The company believes in meritocracy, where ideas and effort are publicly celebrated. Its mission is to deliver one platform for maintenance, repair, and operations teams to keep the physical world running, prioritizing people as the greatest asset. MaintainX is committed to creating a diverse environment and considers all qualified applicants without regard to race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or veteran status.