--- title: Re-imagining ML Serving Infra: My Winter Internship at Ramp description: An intern on Ramp's ML Platform team describes building a dedicated model serving layer called mw-serve during a 14-week winter internship. The project aimed... canonical: https://daily.dev/posts/re-imagining-ml-serving-infra-my-winter-internship-at-ramp-jieac5sno twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Re-imagining ML Serving Infra: My Winter Internship at Ramp | daily.dev og:description: An intern on Ramp's ML Platform team describes building a dedicated model serving layer called mw-serve during a 14-week winter internship. The project aimed... og:url: https://daily.dev/posts/re-imagining-ml-serving-infra-my-winter-internship-at-ramp-jieac5sno og:image: https://api.daily.dev/og/posts/jIEAC5Sno.png og:image:alt: Re-imagining ML Serving Infra: My Winter Internship at Ramp og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Re-imagining ML Serving Infra: My Winter Internship at Ramp **[Ramp Engineering](https://daily.dev/sources/ramp_eng)** · 6 min read · 0 upvotes · 0 comments ## Summary An intern on Ramp's ML Platform team describes building a dedicated model serving layer called mw-serve during a 14-week winter internship. The project aimed to decouple ML model serving from the intelligence platform (intel plat), a high-uptime service processing ~10M requests/week for fraud detection and credit underwriting. The solution containerizes models with their training environments using ECR and MLflow, enabling dependency isolation. Key engineering challenges included meeting a ~15ms latency budget for card transaction fraud detection, diagnosing tail latencies caused by Python GC pauses blocking the GIL, and adding observability to each component of the inference pipeline. By the end, one model was serving in production with others in shadow mode. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Day 96: AI Model Serving — Taking AI From Research to Production](https://daily.dev/posts/day-96-ai-model-serving-taking-ai-from-research-to-production-zulmnlgzb) · Medium · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#python](https://daily.dev/tags/python), [#containers](https://daily.dev/tags/containers) [View this post on daily.dev](https://daily.dev/posts/re-imagining-ml-serving-infra-my-winter-internship-at-ramp-jieac5sno) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Re-imagining ML Serving Infra: My Winter Internship at Ramp","url":"https://daily.dev/posts/re-imagining-ml-serving-infra-my-winter-internship-at-ramp-jieac5sno","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/re-imagining-ml-serving-infra-my-winter-internship-at-ramp-jieac5sno"},"datePublished":"2026-07-08T19:14:48.210Z","dateModified":"2026-07-08T19:15:26.650Z","description":"An intern on Ramp's ML Platform team describes building a dedicated model serving layer called mw-serve during a 14-week winter internship. The project aimed...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0a35f01a520a823373531c4e05dac383?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0a35f01a520a823373531c4e05dac383?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Ramp Engineering","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Ramp Engineering","logo":"https://media.daily.dev/image/upload/s--4x5H_pLU--/f_auto/v1704280953/logos/ramp.jpg","url":"https://daily.dev/sources/ramp_eng"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/re-imagining-ml-serving-infra-my-winter-internship-at-ramp-jieac5sno","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,python,containers","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Ramp Engineering","item":"https://daily.dev/sources/ramp_eng"},{"@type":"ListItem","position":3,"name":"Re-imagining ML Serving Infra: My Winter Internship at Ramp"}]} ```