Youre the kind of engineer who thrives on solving complex data challengesdesigning and optimizing data pipelines that fuel AI-driven insights. Whether its ingesting massive streams of data, wrangling unstructured data, or optimizing embeddings for fast retrieval, you love making data work at scale. Your curiosity drives you to challenge conventional thinking, and you care deeply about the user experience and strive to build products that empower users. Now, imagine applying that expertise to a game-changing AI platform thats transforming how public affairs professionals track issues, anticipate risks, and make smarter decisions.At Delve Deep Learning (DDL), were not just building another AI productwere changing the way public affairs professionals work and navigate the world. We need a Data Engineer who can architect robust data ingestion systems, streamline pipelines, and enrich data to power state-of-the-art AI-driven knowledge discovery.If youre excited about large-scale scraping, ETL, data enrichment, chunking strategies for LLM embeddings, and optimizing AI-driven data retrieval, this is your opportunity to make a major impact.A Quick Note: If job descriptions were checklists, most of us would never get hired. If youre excited about this role but dont meet every single requirement, thats okayIf you think youd be great at this job, wed love to hear from you.What Youll DoBuild and Optimize Data Ingestion & ScrapingDesign and maintain large-scale web scraping and data ingestion pipelines.Implement robust scraping frameworks to collect structured and unstructured data from diverse sources.Ensure reliable data extraction, deduplication, and normalization.Build and Scale Data PipelinesDevelop scalable ETL workflows for processing and transforming large datasets.Automate data ingestion, storage, and retrieval processes.Optimize pipeline performance for speed, cost efficiency, and reliability.Enrich and Structure Data for AI ModelsDevelop data cleaning and enrichment techniques to improve data usability.Design entity resolution, linking, and metadata augmentation workflows.Implement data normalization.Optimize Data Chunking and AI RetrievalWorking with the team, help experiment with chunking strategies to optimize embeddings for vector search.Support implementing best practices for tokenization, windowing, and text segmentation.Ensure high-accuracy retrieval performance for AI-powered search and recommendations.Scale Data Infrastructure and APIsDesign and manage data warehouses and vector databases for fast retrieval.Implement robust APIs to serve data efficiently to AI models and applications.Monitor and optimize data pipelines for high availability and performance.Who You AreStrong Engineering Background You have at least 3 years of experience engineering solutions to complex data challenges. Fluent In Python You can write python in your sleep.An Expert in Data Ingestion & Scraping You have experience with large-scale web scraping frameworks (Scrapy, Selenium, Playwright) and data ingestion pipelines.A Strong ETL & Data Pipeline Engineer Youve built scalable data workflows.Fluent in SQL & NoSQL Youre comfortable with Postgres or similar databases.Experienced in Data Processing & Enrichment Youve worked with NLP techniques, entity resolution, or metadata augmentation.Knowledgeable in Vector Databases & Chunking You understand embedding chunking strategies and have worked with tools such as FAISS, Pinecone, or PostgresSQL vector DB.Skilled in Cloud & Infrastructure Youre experienced with AWS for data engineering workloads.Bonus Points If You:Have experience with Django or similar Python web frameworks.Have built AI-powered SaaS products or large-scale knowledge retrieval platforms.Why Join Us?Youll Help Build the Data Backbone of AI Your work will power cutting-edge AI-driven insights for public affairs professionals.Work With A Sharp And Innovative Team Were assembling a team of top-notch engineering talent.We Move Fast And Nimbly Youll work in a high-velocity startup where your ideas and execution matter.Competitive Pay & Strong Benefits Salary range of $100,000 to $180,000 (based on experience), stock options, health insurance, 401(k) matching, and more.Hybrid Flexibility Work a hybrid schedule from our Washington, D.C. office with a fitness center.If youre excited about building cutting-edge AI systems for real-world impact, we want to hear from you.Apply today and help shape the future of AI-driven intelligence. recblid oqqefb5h9zg2ob85nre11dngj1fm1g