Hi, I'm
Sarah Salah
Computer Scientist - AI specialist
Architecting the next generation of intelligent systems, where AI meets infrastructure, and complexity becomes clarity.
01. About Me
Who I Am
I'm an AI Researcher, Developer & Software Architect exploring the boundaries between intelligence, systems, and the mathematics that ties them together. I write Python to build miracles, and C just for fun.
My research focuses on uncertainty in AI understanding what models know, what they don't, and how to build systems that reason honestly about their own limits. I believe the next frontier in AI isn't just capability, it's self-awareness.
I'm an active contributor to open-source projects and a lifelong student of mathematics, convinced that the best engineers are the ones who never stop being curious.
02. Skills
Tech Stack
AI & Machine Learning
AIOps/MLOps & Infrastructure
Software Architecture
Data & Search
DevOps & Cloud
Backend Development
03. Projects
What I've Built
Kubernetes MCP — Open Source Package
Published an open-source Model Context Protocol (MCP) server for Kubernetes enabling AI agents to interact with K8s clusters through natural language. Available on PyPI for the global developer community to install and extend.
From Data Center to AWS Cloud
Designed an end-to-end migration architecture that moves enterprise workloads from on-prem data centers to AWS — without the rewrite penalty. Built around EKS for compute, managed services for state, and incremental rollouts that prove value at every step.
OpenObserve Log Intelligence
Built intelligent log querying and analysis pipelines on OpenObserve enabling real-time namespace/container filtering, time-range queries, and anomaly surfacing at production scale. Designed for cost-efficient observability in cloud-native environments.
AI Service Catalog
Designed and deployed an internal AI service catalog for on-premise environments, enabling teams to discover, consume, and monitor ML models via a unified API layer.
Internal Conversational AI Platform
Designed and built a self-hosted conversational AI platform tailored to internal business needs, featuring custom dialogue management, NLP-driven intent recognition, and a flexible chat flow engine. Architected as a scalable, open-source alternative to proprietary solutions.
LLM Self-Hosting on Kubernetes
Deployed and optimized open-weight LLMs (Qwen3 72B, LLaMA) on 4x NVIDIA L40 GPUs using vLLM with tensor parallelism, served via Kubernetes with full observability stack.
04. Blog
Latest Writing
The Art of Reverse Engineering
A deep dive into the methodology of reverse-engineering proprietary systems and rebuilding them as open alternatives ,the process, the challenges, and the lessons learned.
Read more →Staying Sane in the AI Race: How to Actually Keep Up
Practical strategies for navigating the overwhelming pace of AI advancement ,what to read, what to skip, and how to build lasting intuition in a fast-moving field.
Read more →05. Contact
Get In Touch
Available for freelance projects, consulting, and interesting collaborations. Feel free to reach out, I usually respond within 24 hours.