You will get a Manual Workflow Automation with Claude & Python
Rising Talent
Rising Talent
Project details
If a person on your team spends hours every week copying data between systems, cleaning messy files, reading documents and re-typing what's in them, or checking one source against another, that's automatable. I build the thing that does it.
Plain Python where plain Python is right. Claude where the step actually needs to read, understand, or decide. No AI bolted on for show, and no fragile macro that breaks the first time a file looks slightly different.
You work directly with me start to finish. I build it to handle the messy version of your data, not just the clean sample, because the messy version is what shows up on a Tuesday.
What this looks like in practice:
• Pull data from a few sources, reconcile it, output one clean file or sheet
• Read PDFs or scanned documents and turn them into structured rows
• Match records across two systems that do not share an ID
• Watch for a trigger, do the work, hand back the result
Recent build: I reconciled commission data from 7 different insurance providers, each with its own format, into one clean output, and delivered it as a reusable Claude skill the client now runs himself with no developer in the loop.
Plain Python where plain Python is right. Claude where the step actually needs to read, understand, or decide. No AI bolted on for show, and no fragile macro that breaks the first time a file looks slightly different.
You work directly with me start to finish. I build it to handle the messy version of your data, not just the clean sample, because the messy version is what shows up on a Tuesday.
What this looks like in practice:
• Pull data from a few sources, reconcile it, output one clean file or sheet
• Read PDFs or scanned documents and turn them into structured rows
• Match records across two systems that do not share an ID
• Watch for a trigger, do the work, hand back the result
Recent build: I reconciled commission data from 7 different insurance providers, each with its own format, into one clean output, and delivered it as a reusable Claude skill the client now runs himself with no developer in the loop.
AI Algorithms
Large Language Model, Multimodal Large Language Model, Transformer ModelAI Applications
Natural Language Generation, Natural Language Understanding, Text RecognitionAI Development Language
PythonAI Models
ChatGPT, OpenAI CodexWhat's included
| Service Tiers |
Starter
$1,000
|
Standard
$2,000
|
Advanced
$3,500
|
|---|---|---|---|
| Delivery Time | 14 days | 21 days | 28 days |
Number of Revisions | 1 | 2 | 3 |
AI Model Integration | |||
Batch Normalization | - | - | - |
Database Integration | - | ||
Detailed Code Comments | |||
Image Upscaling | - | - | - |
MLOps | - | - | - |
Model Deployment | - | - | |
Model Documentation | |||
Model Monitoring | - | - | |
Model Testing & Optimization | - | ||
Model Tuning | - | - | - |
Natural Language Processing | |||
NLP Tokenization | - | - | - |
Pre-Training | - | - | - |
Prompt Engineering | |||
Setup File | |||
Source Code |
Optional add-ons
You can add these on the next page.
Fast Delivery
+$300 - $400
Additional integration / data source
(+ 3 Days)
+$400Frequently asked questions
1 review
(1)
(0)
(0)
(0)
(0)
This project doesn't have any reviews.
AM
Alan M.
Jun 15, 2026
Senior Data Engineer: Scale a Multi-Marketplace Catalog & Normalization Engine (PostgreSQL / Python)
Muhannad is great to work with and is a clear communicator which I value a lot. Will hire him again.
About Muhannad
Claude Code & AI Agent Engineer | Python Automation, LLM Pipelines
Cairo, Egypt - 5:35 am local time
Recent builds:
- A 7-skill, 18-state Claude Code offboarding engine: 4 sub-agents, hook-enforced guardrails, and a JSONL event log as the single source of truth so every run is auditable.
- Commission reconciliation across 7 insurance providers, each with its own format, delivered as reusable Claude skills the client now runs himself.
- A cross-marketplace product matcher at 99.2% precision, with an "abstain rather than mismatch" rule so it stops instead of guessing wrong.
- A 17-gate Python QA pipeline plus a two-pass LLM-judge review fleet for a fine-tuning dataset.
- A GEO upgrade for a news publisher, built with Claude Code and automated schema verification.
- A multi-source data pipeline delivered solo through an agentic Claude Code workflow: 3 databases → one audited, queryable product, solo.
When a no-code tool hits its ceiling (branching logic, state, real error handling), that's where I take over. I rebuild the workflow in code so it does what you actually meant, keeping the parts that worked.
I work best on projects where:
- The input and output are clear, even if the data in between is messy
- There is real API integration, data wrangling, or an AI/LLM workflow involved
- You need something built, tested and handed over, not just advised on
Why Claude-native matters: it's the model family I design around full time, so I know its failure modes and build around them instead of being surprised by them. If your project needs a different model for one step, I will tell you and wire it in. The goal is a system that holds up, not loyalty to a logo.
Stack: Claude Opus/Fable, GPT-5.5, Python, Node.js, OpenRouter, Tesseract, faster-whisper, Playwright, Pandas, SQL.
Steps for completing your project
After purchasing the project, send requirements so Muhannad can start the project.
Delivery time starts when Muhannad receives requirements from you.
Muhannad works on your project following the steps below.
Revisions may occur after the delivery date.
Map the task
I follow how it is done by hand today, including the messy edge cases, so the automation handles the real version of your data, not just the tidy sample.
Build the pipeline
Plain Python for structure, Claude for the steps that need judgment (reading documents, matching records). Built in your repo, on your keys.