← back
Building LinkedIn's GenAI Platform — Xiaofeng Wang
Original: Building LinkedIn's GenAI Platform — Xiaofeng Wang
Takeaway
LinkedIn's GenAI platform evolved through three generations to support multi-agent systems with distributed orchestration, a skill registry, layered memory, and OpenTelemetry-based observability.
Summary
- Xiaofeng Wang traces LinkedIn's GenAI platform from 2023 'Collaborative Articles' (single GPT-4 prompt, Java+Python stacks) to a unified Python SDK on top of LangChain.
- Second generation: 'Coach' RAG-based job-fit assistant — added prompt management, source-of-truth prompts, conversational memory infrastructure.
- 2024: first multi-agent system 'LinkedIn Hiring Assistant' for recruiters; platform added distributed agent orchestration, retry, traffic shifting, and a centralized skill registry for tool discovery.
- Memory expanded from conversational to experiential memory with working/long-term/collective layers; observability built on OpenTelemetry given autonomous-agent unpredictability.
genai-platformmulti-agentlinkedin
Original description
In this talk, we will offer insights into building LinkedIn’s GenAI Platform team from the perspective of a first-line manager. We will explore the journey of developing a scalable and adaptable GenAI technology stack in a rapidly evolving tech landscape, seamlessly integrating AI-first principles into LinkedIn’s predominantly Java-based ecosystem, and achieving significant advancements in multi-agent system architectures. The presentation will highlight LinkedIn's GenAI platform innovations, including a centralized registry for dynamic skill-sharing, contextual memory for agent interactions, seamless integration with existing infrastructure, and a balanced approach to leveraging both in-house solutions and popular open-source libraries. Attendees will gain practical insights into fostering collaboration, cultivating a developer-friendly environment, aligning agile execution with long-term platform goals, and identifying the critical talent and skills essential for success. This talk is designed to inspire and guide leaders as they build foundational GenAI teams in dynamic, fast-changing environments. Recorded live at the Leadership Track Session Day from the AI Engineer Summit 2025 in New York. Learn more at https://ai.engineer and purchase tickets to our next event, the AI Engineer World's Fair, in SF June 3 - 5 here: https://ti.to/software-3/ai-engineer-worlds-fair-2025 About Xiaofeng Xiaofeng Wang leads a full-stack AI engineering team at LinkedIn, spearheading the development of cutting-edge Generative AI technologies. Their team focuses on LLM post-training optimization, crafting application frameworks, agent architectures, and researching the latest advancements in post-training techniques. They bring innovative solutions to production, empowering agentic applications and products that transform user experiences at LinkedIn.