recruiting · saas · workflow
Upwork scales custom AI models with Uma to cut job post creation time 80% and improve work outcomes
Upwork needed to serve a large and growing customer base that expected AI solutions, but general-purpose LLMs lacked the precision and contextual awareness needed for marketplace-specific tasks like job post creation and candidate matching.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Client triggers job post creation
A client needs to create an effective job post for a complex project.
Tools used
UmaJob Post GeneratorUpwork Chat ProGPT-3.5GPT-4ClaudeGPT-4oLlama3.1
Outcome
The Job Post Generator reduced time to posting by 80% for clients, and the custom Uma model delivers more precise, conversational guidance by drawing from Upwork's historical platform signals, boosting freelancer productivity and work quality.
What failed first
Standard pretrained LLMs produced vague, imprecise responses drawn from broad internet data and were unable to hold conversations that progressively learn about specific user needs, limiting their usefulness for Upwork's marketplace challenges.
Results
Time saved80%
Running sincethis year
Grounding & classification
Source type: technical build writeup
34 fields verified against source quotes.
content generationconversational aienterprise searchpersonalizationrecommendation systemform submissionknowledge basefailure mode describedmetric backedproduction runtime claimedtools describedvendor confirmedworkflow describedsoftwareemployee productivitytime savedtechnical build writeuphr opsrecruitingai draft human approvalrag answering