recruiting · saas · workflow
LinkedIn builds a multi-step ML pipeline to extract and map skills from content into the LinkedIn Skills Graph
Skills embedded in member profiles, job postings, and learning course descriptions are often absent from dedicated skills sections, making comprehensive and accurate mapping to the LinkedIn Skills Graph difficult.
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 · Profile or content update triggers extraction
LinkedIn's member profile skills feature requires nearline inference when a member profile is created or updated.
Tools used
LinkedIn Skills GraphMultilingual BERTTransformerKnowledge DistillationSamza-BEAMSpark
Outcome
The multitask learning framework for job-important skills yielded improvements across job recommendation, job search, and job-member skill matching, with Knowledge Distillation reducing the model size by 80% without compromising performance.
Results
Volume80%
Cost replaced+0.7577%
Grounding & classification
Source type: technical build writeup
34 fields verified against source quotes.
data extractionenterprise searchrecommendation systemknowledge baseresumehuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwareaccuracy improvementconversion increasethroughput increasetechnical build writeuphr opsrecruitingextract classify route