Explore the full engineering blog here: https://www.linkedin.com/blog/engineering/generative-ai/how-we-built-domain-adapted-foundation-genai-models-to-power-our-platform

This blog details LinkedIn's development of domain-adapted foundation models, called EON models, to power their GenAI platform. These models, built upon open-source models like Llama, are enhanced with LinkedIn's Economic Graph data for improved performance and cost-effectiveness. A key application is the Hiring Assistant, where EON models significantly improved candidate-job matching accuracy. The development process involved multi-task instruction tuning, safety alignment, and rigorous benchmarking against state-of-the-art models. Future work focuses on expanding EON's capabilities for more complex, multi-step interactions.