Filip Makraduli (@f_makraduli)
AI Engineer Europe 2026에서 Small Model Inference 발표 내용을 공유한 트윗입니다. 인프라와 딥한 모델 아키텍처 이해를 결합해야 소형 모델 추론을 제대로 최적화할 수 있다는 점을 강조합니다.
My pleasure to finally share my talk at AI Engineer Europe 2026 @aiDotEngineer on Small Model Inference and how you need to combine infrastructure with deep model architecture understanding to make this work. Thanks @swyx for making this event happen! https://t.co/LJDFBz3t91
📝 What kind of MLOps team are you? [Part 3/3]
#mlops #productionml #dataops #mlsystems
In early starts-ups & even at the Small/Med Size business, teams are often a combination of the different modes & that's totally fine!
You don't always need a specialized team!
💡What's important to recognize is to know this framework exists for organziational alignment, as well as to know when teams can be spun out.
📝 What kind of MLOps team are you? [Part2/3]
#mlops #productionml #dataops #mlsystems
🔍 Zeroing in on the ones that oftentimes constitute the ML Org or the Data org:
⛑ Enabling teams - Help the DS & Product folks get those models out the door using the internal plateforms & capabilities provided by the CST
⚙️ Complicated Subsystem team - Focused on maintaining & expanding the extremely technical solution they own
👷🏻♀️The Platform Team - Owns unified & integrated experience.
📝 What kind of MLOps team are you? [Part1/3]
🗺️ In the world of "team Topologies" there are 4 types of teams.
🌊 Stream-aligned teams (ST) ---------> Data science & Product (for example)
⛑ Enabling teams (ET) ---------> ML Engineering
⚙️ Complicated Subsystem team (CST) ---------> The Kubernetes Team, the GCP team, the Terraform team, the Redis team, etc
👷🏻♀️The Platform Team (PT) ---------> The ML Platform Team, The Data Platform Team, etc
👉🏻 Online Inference =/= Streaming
We're all aware of this right? That they're not the same thing?
#mlops #mlengineering #datascience #dataengineering #productionml #mlsystems #systemdesign
So don't let the shift in topic to Data-Centric AI fool you into thinking modeling, algorithms, feature engineering, etc aren't important.
Instead see the focus of convo on data as an acknowledgement of an impactful area that has been underappreciated in its impact on ML.
If you talk to most serious athletes or bodybuilders, they'll tell you how important diet is in achieving their goals. (Hint: The phrase "Abs are made in the kitchen")
But they'll also wax lyrical about
✔️ their splits (upper vs lower, arms/shoulders/core vs back/chest vs legs),
✔️ how much they hate cardio (which I find inexplicable as secretly they love it, they just say they hate it because everyone else says it),
✔️ their cheat meals.
❓❓ What is the difference between Model-Centric AI vs Data-Centric AI ❓❓
By analogy:
👉🏻 #ModelCentricAI ➡️ The workout matters 🏋🏻♀️
👉🏻 #DataCentricAI: ➡️ The diet matters 🥗
So the difference between Model-Centric AI and Data-Centric AI is like optimizing on the workout (types of lifts, cardio, reps & intensity, etc) versus optimizing the diet (caloric intake, macros, timing, etc).
sayzard
Mikiko