Skip to content
View oabdrabo's full-sized avatar
2 followers · 3 following

Sponsoring

@vllm-project

Achievements

Achievement: Public SponsorAchievement: QuickdrawAchievement: YOLOAchievement: Pair ExtraordinaireAchievement: Pull Sharkx2

Achievements

Achievement: Public SponsorAchievement: QuickdrawAchievement: YOLOAchievement: Pair ExtraordinaireAchievement: Pull Sharkx2

Organizations

@pyxis3-ai

Block or report oabdrabo

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
oabdrabo/README.md

Hi, I'm Omar 👋

Founder of PYXIS3 — autonomous AI for infrastructure operations

London · production AI & cloud infrastructure · LLM inference serving · Kubernetes-native operations

PYXIS3 LinkedIn Email

Currently · Open source · Writing · Experience · Stack · Contact

Currently

  • Founder, PYXIS3 (@pyxis3-ai) — autonomous AI that runs your cloud and data-center infrastructure operations across AWS, Google Cloud, Azure, VMware, Nutanix, and on-prem, spanning cost, capacity, reliability, security, and governance, within your guardrails. One subscription, never a share of savings.
  • Senior Solutions Engineer, Seldon — the production MLOps platform: vLLM-based LLM inference and multi-tenant model serving on Kubernetes.

Author of the canonical AWS guide on decoupling RDS from Elastic Beanstalk — the same procedure AWS's official YouTube channel cites as "Watch Omar's video to learn more."

Open source

Most under @pyxis3-ai:

Project What it is
lens In-cluster Kubernetes observability with in-browser kubectl exec. Vue 3 + Bun, single binary, ServiceAccount-token auth — built for ML-serving and GPU clusters.
vllm-bench Throughput + latency benchmark for OpenAI-compatible LLM endpoints (vLLM, TGI, llama.cpp, Ollama). TTFT, TPOT, token throughput at percentiles. Async, two dependencies. · MIT
llm-serving-cookbook Production recipes for K8s-native vLLM-first serving: vLLM-on-EKS, KEDA autoscaling, token economics, TTFT optimisation, runtime selection. · Apache-2.0
awesome-model-agnostic-llm Curated index of model-agnostic LLM tooling: runtimes, routers, evaluators, observability, standards, open weights. · CC0
noor Semantic search over the Quran + Hadith corpus. Arabic-aware multilingual embeddings on sqlite-vec. FastAPI + Vue, single Docker image.
DisplayDeck Personal — a tiny macOS menu-bar app for total display control (disable screens, Force HiDPI, EDR brightness, warmth, window transparency/PiP, keep-awake). Objective-C on private CoreGraphics/SkyLight APIs. · MIT

Writing

Experience

Company When Role
Seldon Technologies 2025–present Senior Solutions Engineer — production MLOps: vLLM inference, multi-tenant serving on Kubernetes.
AWS · London 2022–2025 Solutions Architect, Industry Specialist for semiconductors — AI/ML on Inferentia, Trainium, SageMaker, Bedrock.
AWS · Cape Town 2017–2022 Cloud DevOps Engineer — authored two AWS Knowledge Center articles + the companion YouTube video.
Dell EMC 2016–2017 Storage engineering (Isilon).
IBM 2016 Cloud infrastructure.
OrecX, HONEST · Egypt 2007–2012 Earlier work.

Stack

vLLM · Triton · Kubernetes · KEDA · Helm · Prometheus · Caddy · AWS · GCP · Azure · Python · Go · TypeScript

Contact

Founder @pyxis3-ai · building autonomous infrastructure operations

Pinned Loading

  1. pyxis3-ai/lens pyxis3-ai/lens Public

    AI/LLM-serving observability for Kubernetes. Inspect vLLM/TGI/llama.cpp inference pods, browse resources, kubectl exec in-browser. Single Bun binary, in-cluster SA-token auth.

    Vue 1

  2. pyxis3-ai/noor pyxis3-ai/noor Public

    Multilingual AI semantic search (Arabic + English). Sentence-Transformers embeddings + sqlite-vec vector store + Arabic NLP normalisation. Sub-second on CPU. Quran + Hadith demo corpus.

    HTML 1

  3. pyxis3-ai/vllm-bench pyxis3-ai/vllm-bench Public

    Throughput + latency benchmark for OpenAI-compatible LLM endpoints (vLLM, TGI, llama.cpp, Ollama). TTFT, TPOT, throughput, percentiles. Runtime-agnostic.

    Python 1

  4. pyxis3-ai/awesome-model-agnostic-llm pyxis3-ai/awesome-model-agnostic-llm Public

    Curated list of open-source LLM-serving runtimes, routers, evaluators, and standards. Run LLMs without locking into one vendor.

    2 3

  5. pyxis3-ai/llm-serving-cookbook pyxis3-ai/llm-serving-cookbook Public

    Production recipes for running open-source LLMs on Kubernetes. vLLM-first. vLLM-on-EKS, KEDA autoscaling, token economics, TTFT optimisation, runtime selection.

    2

  6. DisplayDeck DisplayDeck Public

    🖥️ Tiny macOS menu-bar app for total display & window control — disable screens, Force HiDPI, brightness boost, warmth, transparency/blur/pin/PiP, keep-awake.

    Objective-C 8 1