ENGINEERING PORTFOLIO
MERT’S MIND
LLM SYSTEMS / PYTHON / PLATFORMS
01 / OPERATOR PROFILE · NETHERLANDS

Mert Alnuaimi

Principal Software / Platform Engineer · Python & Applied AI

I build Python services and the platforms they run on. On the AI side I’ve shipped a RAG chatbot that answers in Turkish and built context routing for a coding agent. Right now I’m building a coding agent with its own independent grader, to get better at measuring whether any of this works.

I BUILD IT,
THEN I RUN IT.

AI work

02 / THE WORK
01 / RAGLive

RAG chatbot over an author’s writing

Answers questions from Ramazan Demir’s published writing, and refuses when his sources don’t cover it. I built the retrieval side, and every prompt change has to pass 40 hard benchmark questions first.

  • LangChain
  • OpenAI embeddings
  • GPT-5.4
  • Amazon Bedrock
  • FastAPI / Cloud Run
02 / AGENT TOOLINGMy own workflow

Context routing for a coding agent

A typed classifier picks which context a coding agent needs before it opens any files. It never grants permission to change anything.

  • Python
  • TypeSafe (jev-latest)
  • Context selection
03 / EVALSIn progress

Coding agent lab, graded separately

A local coding agent fixes bugs; a separate container grades each patch with hidden tests. The first baseline passed 15 of 15, so the tasks were too easy. Harder ones are next.

  • Agents
  • Evals
  • Ollama
  • Docker
04 / FINE-TUNINGLab experiment

Fine-tuning an 8B model for format

QLoRA on Llama 3.1 8B, trained on a 16 GB MacBook and graded by my own checker. Neither model invented a figure; the fine-tune hit the house format 50 of 50 times, against 0 for the prompt alone.

  • Llama 3.1 8B
  • QLoRA / MLX
  • Evals
  • Synthetic data
05 / SPEECHClient project

Multi-speaker voice training

A client’s answer robot needed to speak. I built the data pipeline from raw recordings to transcribed, tested training splits, picked speakers by pitch, and trained a multi-speaker VITS model on rented GPUs.

  • PyTorch
  • ESPnet2 / VITS
  • faster-whisper
  • Audio processing

Production engineering

03 / OWNERSHIP
MOBIQUITY · NOV 2025 – PRESENT

Brit Insurance

Principal Software Engineer, via Mobiquity

I own two FastAPI services other teams depend on: an orchestrator and the layer that stores its data. Mostly that means API contracts, performance, and environments that build the same way on a laptop and in the pipeline.

Explore the services ↗
RABOBANK · 2021–2025 · VIA MOBIQUITY

Datakeeper / Rabobank

Principal Engineer from Jul 2023, Senior+ Platform Engineer before that

My first four years at Mobiquity were on this project, from day one. I rebuilt the AWS platform in Terraform, put logs from 10 production accounts in one place, load-tested before setting the autoscaling, and built the RAG chatbot on datakeeper.nl.

Centralized logging ↗Explore the platform ↗

Inside the mind

04 / OPTIONAL EXPLORER

The longer version, if you want it. Pick a node or a file.

02 / SYSTEM EXPLORERCH. 00
CORE SCANINTERACTIVE MAP
Pick a
node.
Mert’s mind: a brain connected to platforms, Python, and artificial intelligence MERT’S MIND
SELECT A NODE TO EXPLORE
COMPLEXITY IN. CLARITY OUT.
03 / DOSSIER READER▣
FILE 00INTRODUCTION
A LITTLE CONTEXT

I build it,
then I run it.

I build Python services and the platforms they run on, with ownership of contracts, performance, and delivery.

01

Right now

Principal engineer on Brit Insurance, through Mobiquity. I own two FastAPI services: the orchestrator, and the layer that stores the data.

02

On the side

A coding-agent lab with a separate grader. It’s where I practise evals, fine-tuning, retrieval testing, MCP, and running models locally.

03

Earlier

Four years on Datakeeper, a Rabobank identity wallet. Before that, DevOps for Vatan Bilgisayar, a Turkish electronics store: Kubernetes, caching, pipelines.

PYTHONAWSNETHERLANDS
THE NOTEBOOK 05 NOTESField notes

Write-ups with the actual code: RAG context limits, typed routing for a coding agent, a QLoRA fine-tune, voice training, and a few platform pieces.

OPEN THE NOTEBOOK
05 / LET’S TALK

Get in touch

If you’re hiring for software, platform, or applied AI engineering, LinkedIn is the quickest way to reach me.

Contact Mert on LinkedIn ↗Explore my GitHub ↗