Niv Yungelson
Member of the technical staff at Accomplish|AWS Community Hero and leader| Public speaker
Tel Aviv, Israel
Actions
Hi! I’m Niv - an early tech enthusiast from before “DevOps” was even a word. I’m a member of acomplish.ai technical staff and AWS Community Hero, co-leading the AWS Israel User Group where I help connect and empower builders. I love sharing knowledge through public speaking and I’ve had the privilege of speaking at events like AWS re:Invent, KubeCon, DevOpsDays, and Geektime Code.
Area of Expertise
Topics
We Tried OSS Model Routing Tools So You Don’t Have To
Modern AI applications are no longer single prompts. They are pipelines of decisions: retrieval, reasoning, tool use, and execution. However, most systems still default to a single model across all steps, leading to unnecessary cost, latency, and failure modes.
This talk presents a hands-on evaluation of open-source model routing tools in the context of multi-step AI workflows. Instead of comparing models in isolation, we examine how routing decisions change when facing a multi-step pipeline as part of computer-use task execution.
We’ll cover real experiments, architectural patterns, and common pitfalls, and provide a practical approach to step-aware routing that improves both performance and cost efficiency.
When infra IS code- Operations in a serverless world
You cannot detach engineering processes and culture from the infrastructure.
In this talk we will share from our experience of supporting and managing serverless production environments. We will discuss the not-so-obvious way it differs from managing other more common modern infrastructures and the impact it has on the operations methodology. we will discuss how it influences the developers day to day work and lessons learned.
SRE Not Sorry
Everyone is looking for top notch developers. Many companies strive to have the "next challenge" that these ninja super stars are looking for, but at what cost? is it worth over complexing your architecture with buzz-word technologies in order to make the position seem more attractive?
In this talk I will share my experience as a DevOps team leader the implications of over-engineering. I will give a walk through about what DevOps was originally created for and what it evolved to in these days, and share guidelines on how to find the middle ground between operation, development and excitement.
Newsflash: There is no Quality as a Service
Our hardware is getting faster, why the heck does our software get slower?
our servers are virtual at best. Our databases use storage that is not managed by us and our code is on someone else’s domain.
In this talk we will speak the unspeakable- over-abstractions can hurt the quality of our product and we don’t do anything about it.
I will give examples of before and after, and alongside to a lot of food for thought, we will give some practical tips on how to be quality minded in a world of SaaS
First Order Fundamentals to Ramp Up Your SRE Practice
Site reliability engineering must optimize for cost, performance and stability, but it must do so without affecting other critical aspects of engineering such as velocity or developer experience and developer happiness.
In this talk we'll walk through the fundamentals for how to build your SRE strategy––particularly as a first or early hire that needs to build the strategy from the ground up.
We'll walk through how to build your SLA, SLO, and SLI strategy to ensure you are constantly focused on business goals, without eating into error budgets and keeping clients happy. As well as how to deliver the performance, cost and stability optimizations required for modern businesses to thrive through proper KPI management.
PlatforMa 2025 Sessionize Event
Leaders In Tech 2025 Sessionize Event
DevOpsDays Tel Aviv 2023 Sessionize Event
DevOpsDays Tel Aviv 2022 Sessionize Event
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top