Browse past weeks of engineering reads.
Developers needed a unified embedding model capable of processing interleaved multimodal inputs (text, images, video, audio, documents) in a single semantic space for tasks like retrieval-augmented generation and visual search.
Netflix needed to efficiently extract and surface key moments from hundreds or thousands of hours of raw video footage for editorial teams to accelerate the creative content production process.
Facebook Groups Search was unreliable at helping users discover and validate community content most relevant to their search queries.
Providing a scalable, efficient search infrastructure that allows AI agents to dynamically create search instances and perform semantic queries across uploaded documents without managing underlying indexing complexity.
LinkedIn's recruitment platform needed richer data signals to improve candidate matching and recruiter success rates.
LinkedIn Sales Navigator's search pipeline had latency issues as query complexity and data volume grew.
LinkedIn's legacy search infrastructure couldn't scale to handle growing query volumes and evolving relevance requirements across its platform.
Airbnb needed to advance its AI, data science, and machine learning capabilities across multiple domains (NLP, optimization, measurement science) to improve its travel and living platform, requiring solutions to challenges in search ranking, recommendation, experimentation, and large-scale data processing.
Airbnb users in the early trip planning stage often lack a clear travel destination, making it difficult to provide relevant recommendations and convert exploratory browsing into bookings.
Enterprise search and AI assistant products like Dropbox Dash need to connect disparate data sources and optimize AI-driven retrieval, but naively querying across siloed data with LLMs leads to poor relevance and brittle prompt engineering.
Dropbox Dash's AI agent struggled with effectiveness when naively providing all available context to the model, leading to degraded performance as irrelevant information diluted the signal needed for accurate, agentic AI responses.
Manual prompt engineering for Dropbox Dash's relevance judge was unreliable, hard to measure, and costly—making it difficult to systematically improve task performance in production.
Dropbox Dash needs to rank and retrieve relevant context across a user's work in real time, requiring low-latency access to precomputed and real-time features for AI-driven search and recommendation models.
Dash's search ranking models required large volumes of high-quality labeled relevance data to train effectively, but human labeling alone was too slow and expensive to scale to the needed coverage.
Dropbox Dash needed deeper understanding of multimodal content (photos and videos) across user files, but processing diverse media types at Dropbox's scale posed efficiency and architectural challenges.
Netflix's Graph Search platform for federated enterprise data required users to write structured queries, limiting accessibility and ease of use despite the system being scalable and configurable.