How LLMs Are Reshaping Recommendation Systems

How LLMs Are Reshaping Recommendation Systems

Author: Software Engineering Daily August 18, 2026 Duration: 47:51

News feeds and recommendation systems have long relied on deep learning architectures that score each candidate item independently. As LLMs have matured, they have opened up a fundamentally different approach, where a system can reason about content the way it reasons about language. However, that power comes with a fresh set of engineering challenges around cost, scale, and evaluation.

LinkedIn recently rebuilt its news feed to treat content recommendation as a sequence modeling problem. The general approach is to predict what a user will want next, much like an LLM predicts the next token in a sentence.

Tim Jurka has worked at LinkedIn for 13 years and is currently a VP of Engineering. In this episode, Tim joins Matt Merrill to discuss how LinkedIn re-engineered its feed, how the team combines LLMs with traditional signals, managing inference costs at massive scale, steering content quality using natural language policies, and more.

Sponsorship inquiries:
sponsor@softwareengineeringdaily.com

The post How LLMs Are Reshaping Recommendation Systems appeared first on Software Engineering Daily.


Dive into the deep end of the world's most ubiquitous programming language with the JavaScript Archives-Software Engineering Daily. This curated collection pulls from the broader archive, focusing entirely on conversations that dissect the ecosystem, its evolution, and its practical application in modern software engineering. Each episode features in-depth technical interviews with engineers, library authors, and industry leaders who have shaped the language. You'll hear detailed discussions on everything from the intricacies of frameworks like React and Node.js to the underlying mechanics of the V8 engine, from deployment strategies to the challenges of building at scale. The dialogue is substantive and geared toward practicing developers, offering insights that go far beyond surface-level tutorials. For anyone who builds with JavaScript, this podcast serves as an essential audio companion, transforming complex topics into accessible, thoughtful dialogue that illuminates the how and why behind the code we write every day.
Author: Language: en-us Episodes: 50

Software Engineering Daily
Podcast Episodes
Hype and Reality of the AI Coding Shift [not-audio_url] [/not-audio_url]

Duration: 57:05
AI coding tools have gone from novelty to core infrastructure in under three years. Today, many devs use AI daily, a substantial share of new code is AI-generated, and expectations for automation are rapidly increasing.…
Unlocking the Data Layer for Agentic AI with Simba Khadder [not-audio_url] [/not-audio_url]

Duration: 49:04
AI agents are increasingly capable of reasoning and performing autonomous work over long periods. However, as agents take on more complex, longer-horizon tasks, keeping them supplied with the right information becomes th…
Agentic Mesh with Eric Broda [not-audio_url] [/not-audio_url]

Duration: 47:23
AI agents are evolving from individual productivity tools into distributed systems components inside enterprises. The next frontier is coming into focus, and it involves large-scale ecosystems of collaborating agents emb…
New Relic and Agentic DevOps with Nic Benders [not-audio_url] [/not-audio_url]

Duration: 46:18
Observability emerged from the need to understand complex software systems, and involves tracking metrics, logs, and traces so engineers can detect and diagnose problems before they affect users. However, modern applicat…
Mobile App Security with Ryan Lloyd [not-audio_url] [/not-audio_url]

Duration: 54:52
Mobile apps have become a primary interface for critical services, including banking, payments, and healthcare. Unlike web applications, much of the logic and intellectual property in a mobile app lives directly on the u…
FastMCP with Adam Azzam and Jeremiah Lowin [not-audio_url] [/not-audio_url]

Duration: 1:06:06
The Model Context Protocol, or MCP, gives developers a common way to expose tools, data, and capabilities to large language models, and it has quickly become an important standard in agentic AI. FastMCP is an open source…
SED News: OpenCode, AI Code vs. Shipped Code, and the LiteLLM Breach [not-audio_url] [/not-audio_url]

Duration: 56:42
SED News is a monthly podcast from Software Engineering Daily where hosts Gregor Vand and Sean Falconer unpack the biggest stories shaping software engineering, Silicon Valley, and the broader tech industry. In this epis…
FreeBSD with John Baldwin [not-audio_url] [/not-audio_url]

Duration: 1:03:31
FreeBSD is one of the longest-running and most influential open-source operating systems in the world. It was born from the Berkeley Software Distribution in the early 1990s, it has powered everything from high-performan…
Cilium, eBPF, and Modern Kubernetes Networking with Bill Mulligan [not-audio_url] [/not-audio_url]

Duration: 57:30
Modern cloud-native systems are built on highly dynamic, distributed infrastructure where containers spin up and down constantly, services communicate across clusters, and traditional networking assumptions break down. L…