Skip to content
View MustafaKemalV's full-sized avatar
4 followers · 4 following

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx3Achievement: Pair ExtraordinaireAchievement: YOLO

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx3Achievement: Pair ExtraordinaireAchievement: YOLO

Block or report MustafaKemalV

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.

Content in all repositories owned by your account will be closed.
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
MustafaKemalV/README.md

  • 💻 Backend-focused full-stack engineer who builds and ships products end to end.
  • 📍 Essen, Germany
  • 🔭 Working on: Nexein, an AI career platform with CV analysis, job matching and an in-app assistant.
  • 📦 Published: three Spring Boot starters on Maven Central for webhook signature verification, tamper-evident audit logs and idempotency keys that survive reactive retries, plus an LLM router on npm.
  • 🧠 LLM work: semantic model routing, multi-agent RAG pipelines on pgvector, and a council of models from six families that debates a decision and leaves the final call to a human.
  • 🧰 Languages: TypeScript, Python, Java, SQL, Go
  • 🧱 Frameworks: Node.js, NestJS, Next.js, Spring Boot, WebFlux, FastAPI, LangChain, LangGraph
  • ⚡ Off-screen: Sailing, reading, and lifting.
  • 📫 mustafakemalv@gmail.com

How I work: every build is a Mark I. Ship it, find what breaks, build the next one better.

Pinned Loading

  1. llm-music-recommendation llm-music-recommendation Public

    RTU B.Sc. thesis: a single- and multi-agent LLM music recommendation system with a RAG pipeline, few-shot in-context learning, and a consistency evaluation.

    Python

  2. orfora orfora Public

    Optimal Routes For All. A semantic router for LLM apps. Cut cost, keep quality.

    TypeScript

  3. audit-chain audit-chain Public

    Tamper-evident, HMAC-SHA256 hash-chained, append-only audit log for Spring Boot. verify() pinpoints where the chain broke.

    Java

  4. idem-client idem-client Public

    Caller-side idempotency: keep a stable Idempotency-Key across reactive retries so outbound calls to an idempotent downstream aren't double-processed.

    Java