recruiting · saas · workflow
How LinkedIn built domain-adapted EON foundation models to power Hiring Assistant candidate matching
LinkedIn's earlier fine-tuned domain-specific model required significant effort to add new features or generalize to new applications, because representative high-quality training data had to be regenerated and the model retrained for each change. Proprietary GPT-4-class models also posed latency and cost concerns.
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 · Recruiter query intake
Hiring Assistant accepts recruiter queries and automates their repetitive tasks.
Tools used
Hiring AssistantEONRAGRLHFDPOLlamaMixtralMistralKubernetesDeepSpeedvLLMMLFlowHDFSGPT-4LM Evaluation Harness
Outcome
In testing, LinkedIn's EON-8B model is 75x cheaper than GPT-4 and 6x cheaper than GPT-4o, and significantly improved candidate-job-requirements matching accuracy in Hiring Assistant, outperforming GPT-4o mini by an absolute 4% and Llama-3-8B-instruct by an absolute 30%. Prompt simplification strategies also reduced prompt size by 30%.
Results
Volume6x
Cost replaced75x
Running sinceOctober 2024
Grounding & classification
Source type: technical build writeup
47 fields verified against source quotes.
agentic workflowai agentcontent generationdata extractionragsummarizationknowledge baseresumehuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwareaccuracy improvementcost reductionemployee productivitytechnical build writeuphr opsrecruitingagentic task executionai draft human approvalextract classify route