Applied AI Engineer

MaintainX • San Francisco, CA

4d

About The Position

MaintainX is a leading mobile-first work execution platform for industrial and frontline teams. More than 13,000 customers use MaintainX to cut unplanned downtime and run better operations. In August 2026, MaintainX became part of Autodesk, joining Autodesk Operations Solutions. Autodesk's strategy is to converge design, make and operate into one continuous lifecycle. The operating data underneath frontier models isn't commoditized, and that's what we own. Document Intelligence is the horizontal engine that turns raw material into structured, trustworthy maintenance knowledge, and into the AI-native entities and answers built on top of it. This role will own the Generation half of Document Intelligence, turning multimodal primitives into schema-valid entities and ensuring quality. The role involves designing and iterating on prompts, defining per-entity target schemas and domain validators, building generation-quality eval datasets and rubrics, assembling multimodal context windows, and choosing the model and token budget per recipe based on quality, cost, and latency tradeoffs. You will report to our Engineering Lead and work closely with the Processing side of Document Intelligence.

Requirements

• Strong applied GenAI craft - prompt engineering, structured output / tool-use, RAG and retrieval-context patterns
• Real eval discipline: you've built datasets and rubrics, measured factuality/relevance/quality, and closed the loop on regressions yourself
• 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

Nice To Haves

• LLM observability / 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

Responsibilities

• Own the Generation half of Document Intelligence: turning multimodal primitives (keyframes, transcripts, OCR) into schema-valid entities like SOPs, and holding the line on quality so "fast" never becomes "fast and wrong."
• 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

Benefits

• Base pay is one part of the package.
• Depending on the role, compensation may also include commission, an annual bonus and equity.
• Benefits differ by country.
• For roles in the United States, Autodesk’s benefits are described at benefits.autodesk.com.
• For roles in Canada and other countries, the plan differs on health coverage, retirement and leave, and your recruiter will walk you through it.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed