AI Search Engineer

About the CompanyShade is scaling and fast. In a year and half, we’ve built out the combined tech of FrameIO (acq by Adobe for $1.275B) and LucidLink ($40M ARR) while combining it with proprietary AI search/labeling. We handle thousands of hours of video and tens of millions of requests every day, and we’re a critical piece of infrastructure for post-production houses, creative agencies, sports teams, and internal media teams at large companies. Customers include Salesforce, Snowflake, Grüns, Hello Fresh, Deloitte, Motorola, Stagwell Media Group, and Lennar. We’re growing 150% QoQ, 120% NRR. Backed by Khosla, General Catalyst, Contrary, Signalfire and Bling.We’re not done yet—rather, we’re just getting started. We’re building the next version of Shade to be the platform solving pain points in storage systems that aren’t even being addressed yet.This includes:Data transfer is unsolvedFrom hot storage → archive storage, cloud → cloud, camera → editor, moving high volumes of data is still flaky, unreliable and difficult.We are building the tooling and UI directly into our platform to make this seamless at scale.Version control is useful for everyoneYou’re an engineer - git history is useful. We’ve built git for creatives because the same concepts are useful for media teams. We save every version and every file as a commit in our database as changes are made.We have the backend built but we need to build the git UI for creatives.Integrate with everythingProject management tools, AI tools, ad generators and everything in between. Someone has to store the data when its moved between platforms. We want to be that layer.Shade is built on Python, NodeJS, NextJS, and C++ with a postgres database.Our core tenets for design areKeep dependencies as minimal as possibleYou are the summation of your subprocessor’s/dependencies issues. To build a durable and reliable company you must be deliberate when you add dependencies and control the vision of all the code you ship.Monolith microservices. Transactional everything requires one database.Solve the core issue. Don’t invent a bandaidEx: if a database query is slow and address it directly rather than reaching for a cache.The simplicity of fs.readFile() always winsHave you tried to access files in a dropbox local drive in your programs? It doesn’t work. Files must be manually downloaded in their entirety to be accessed. We’ve built Shade to be accessible like a hard drive where files are streamed.Building an AI video editor? Works with Shade.Using n8n automations? Works with Shade.Using Davinci resolve? Works with Shade.Our core tenets for the team areWhen we hire we like to keep those hires. Because of this we offer benefits on top of salary + equityFree lunchFree dinnerFully covered health insurance including dental and vision401k with % matchUnlimited PTOLifetime gym membershipCommuter benefit for subwayShipping code happens in personQualificationsThe greatest qualification in our eyes is that you can ship and maintain high volumes of quality code. If you’ve built side projects that are used by thousands of people or worked at companies where you’ve owned features end to end then we’re probably excited about you. What (we think) this looks like in bullet points:3+ years of full-time engineering experienceProven track record of owning AI search or information retrieval systems in production end to endStrong Python experience, including building and maintaining backend services and data pipelinesHands-on experience with LLM-powered search experiences, including retrieval-augmented generation (RAG), evaluation, and prompt and tool design, vector DB (pgvector)Metrics and analytics driven on AI and search performanceExperience with vector databases and vector search (indexing, retrieval, filtering, hybrid search), and an understanding of embeddings and rankingExperience building and operating vector pipelines, including document chunking, metadata enrichment, backfills, and continuous re-indexing (Unstructured.IO, Chonkie)MCP server work is a bonusExperience integrating with RESTful backend servicesGood judgment about system architecture, developer experience, and where tooling and code quality need improvementBased in NYCExperience at a pre-Series B startup