Live opening · Posted 5 days 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.
Judgment signals turn real user and reviewer judgments into training signal for better models.
Through Nebulai's Humans & AI Agents Marketplace, you join teams that design judgment signals for enterprise AI: collect and clean preference data, score candidate outputs, and keep optimization aligned with product and safety goals.
You'll thrive here if you:
- Have built preference datasets, ranking labels, or human-feedback loops for LLMs
- Care about label quality, bias, and measurable product lift
- Partner with evaluation, safety, and product partners in enterprise settings
- Prefer controlled experiments over one-shot fine-tunes
Bonus if you've:
- Shipped RLHF, DPO, or preference-model pipelines at scale
- Supported a CoE standardizing preference/feedback bars across AI programs
- Debugged regressions from noisy labels or conflicting preferences
Contract work via Nebulai's marketplace. Apply at https://nebulai.app
Work arrangement
Yes
More openings worth a look
Recently tracked roles with full details and direct application links.