Full time / Lisbon, PT (Hybrid / Remote)
At Loxy, we empower companies through our flexible digitalization platform, managing teams, fleets, and inventory efficiently.
About MyLOXY
MyLOXY ) is LOXY's next-gen SaaS platform (Angular + Stripe) scaling globally with license management, AI-powered data processing, and partner portals for Europe, MENA, and US.
You'll build the AI-powered data processing system that automatically validates, cleans, and fixes customer data uploads.
The Role
Challenge: Build intelligent data pipelines that handle real-world messy data. Customers upload catalogs, address books, and business data in Excel, CSV, PDFs - often with missing fields, encoding issues, and inconsistencies. Your job: use AI/LLMs to automatically fix what's fixable, alert customers to what needs attention.
What You'll Build:
· Months 1-3: Data upload pipeline, validation, encoding detection, error reporting, Backend API integration
· Months 3-6: LLM-powered data fixing, address normalization, missing field detection, review workflows
· Months 6-12: Batch processing, optimization, quality dashboards, multi-language handling
· Ongoing: Document data patterns, create quality playbooks
Why This Role is Different
AI-First Data Engineering - Not just ETL. Use LLMs (GPT-4, Claude) to intelligently fix data. Prompt engineering is part of the job.
"Data Juggler" - Handle chaos daily. Character encoding nightmares, PDFs with tables, Excel files from hell, CSVs with surprise formats. If perfect data scares you less than messy data excites you, this is your role.
English-Only - All communication, docs, code, commits in English.
Small Team - Work with Backend Developer (API integration) and Frontend Lead (20 years exp). No management layers.
Documentation-First - Document data patterns, transformation logic, LLM prompts. If you don't love documenting, this won't work.
Must-Have
Experience: 3-5 years data engineering/Python | Experience with messy real-world data | Data transformation at scale
Technical: Python (pandas, numpy, data manipulation) | Character encoding handling | File processing (CSV, Excel, PDF) | RegEx mastery | Basic deployment independence
AI/LLM (CRITICAL): OpenAI API, Anthropic Claude API, or similar | Prompt engineering experience | LLM integration in production | This is NON-NEGOTIABLE
Language: Fluent English (C1/C2) - used daily
Mindset: Loves solving data chaos | Problem-solver with ambiguous data | Self-starter | Team player | Quality-focused
Portfolio: GitHub profile mandatory - must see data projects & LLM work
Nice to Have
ETL tools (Airflow, dbt, Prefect) | Cloud (AWS/GCP/Azure) | Web scraping, PDF extraction (tabula, camelot) | FastAPI/Flask | Docker/CI/CD | Data validation frameworks | Vector databases | Langchain
Infrastructure & Tools
Setup: Work with Backend Dev for API integration. Python environment, Docker basics for deployment.
After handoff, you need to:
· Deploy data processing code independently
· Troubleshoot data pipeline issues
· Manage Python environments
· Not be blocked waiting for help
You DON'T need: Full DevOps expertise | Kubernetes | Infrastructure architecture
Red Flags
No AI/LLM experience | No GitHub portfolio | Afraid of messy data | Poor English | "Data analyst" looking to transition | Need perfectly structured data | Can't code well in Python | Expect someone else to clean data
What We Offer
Competitive salary | Health insurance | Flexible hours | Hybrid/remote | Cutting-edge AI/LLM work | Build product's core value prop | Small focused team | Influence from day 1
Apply
Send to:
Subject: Data Engineer (Data Juggler) - MyLOXY Platform
Include:
· CV/Resume
· GitHub profile URL (mandatory) - must show data + AI/LLM projects
· Brief email: Why AI-powered data engineering excites you? Messiest data you've handled? LLM integration experience?
No GitHub with AI/LLM work = No review
Interview Process
5 Steps:
1. Application Review - GitHub profile mandatory (must show AI/LLM work)
2. HR Interview min) - Background, expectations, salary
3. Technical Interview min) - Data challenge, LLM integration, code review
4. Team Fit min) - Meet MyLOXY Backend Dev and Frontend Lead
5. Offer (hopefully)
Timeline: 3-4 weeks from application to offer
--LOXY is an equal opportunity employer. We value diversity and encourage applications from all qualified candidates.
Tipo de oferta: Integral/Full-time