Added
3 hours ago
Type
Full time
Salary
Salary not provided

Related skills

prompt engineering rag genai evaluation llm

πŸ“‹ Description

  • Own Generation for Document Intelligence: turn multimodal inputs (keyframes, transcripts, OCR) into
  • Design and iterate prompts (system, few-shot, context) for each generation recipe.
  • Define per-entity target schemas and validators to ensure output quality.
  • Build generation-quality eval datasets and rubrics; monitor quality regressions.
  • Assemble multimodal context windows so each model call has what it needs.
  • Choose model and token budget per recipe based on quality, cost, latency tradeoffs.

🎯 Requirements

  • Strong applied GenAI craft - prompt engineering, structured output / tool-use, RAG and
  • Real eval discipline: built datasets and rubrics, measured factuality/relevance/quality, closed
  • Shipped LLM features into production services with measurable product impact
  • Comfort with multimodal inputs - video, PDF, audio, image to text or structured output

🎁 Benefits

  • Competitive salary and meaningful equity opportunities
  • Healthcare, dental, and vision coverage
  • 401(k) / RRSP enrollment program
  • Take what you need PTO
  • A work culture that values meritocracy and global collaboration
Share job

Meet JobCopilot: Your Personal AI Job Hunter

Automatically Apply to Engineering Jobs. Just set your preferences and Job Copilot will do the rest β€” finding, filtering, and applying while you focus on what matters.

Related Engineering Jobs

See more Engineering jobs β†’