Applied AI Engineer

📋 Description

• Design and iterate recipe prompts — system, few-shot, and context assembly — for each generation
• Define per-entity target schemas and domain validators (procedure step-type rules, field caps) that
• Build generation-quality eval datasets and rubrics, offline and online, running on LLMX's eval
• Assemble multimodal context windows from keyframes, transcript, and OCR so each model call has
• Choose the model and token budget per recipe based on quality, cost, and latency tradeoffs
• Hand off validated entities to the domains that own them

🎯 Requirements

• Strong applied GenAI craft - prompt engineering, structured output / tool-use, RAG and
• Real eval discipline: you've built datasets and rubrics, measured factuality/relevance/quality, and
• Shipped LLM features into production services, not notebooks, and can connect model performance to
• Comfort working with multimodal inputs - video, PDF, audio, image - converted to text or structured

🎁 Benefits

• Base pay is one part of the package. Depending on the role, compensation may also include