Live opening · Posted 9 hours ago
At a glance
The key details from the original listing.
Your early-applicant advantage
Live timing from JobBeeper.
About the role
Description supplied by the original job listing.
Treat prompts like production code - versioned, tested, and owned - not tribal lore in a Slack thread.
Through Nebulai's marketplace, you lead prompt and system-instruction design for client LLM apps: patterns for RAG, tool use, tone/brand, safety, and eval-driven iteration. Mentor engineers and PMs. Set review standards. Keep quality from drifting as models and use cases change. Vetted talent who deliver.
You'll be a strong fit if you:
- Have led prompt strategy for shipped LLM products (not one-off Playground wins)
- Build eval sets and regression checks around prompt changes
- Write clear system prompts, few-shot libraries, and failure playbooks
- Collaborate with product, legal, and engineering on tone, risk, and UX
Bonus if you've:
- Designed prompt routing across multiple models/providers
- Combined structured outputs with robust parsing and repair
- Trained others via playbooks or office hours
Apply at https://nebulai.app
Work arrangement
Yes
More openings worth a look
Recently tracked roles with full details and direct application links.