AI
Machine Learning Engineer (Document AI) (f/m/d)
You'll build the AI that turns bank statements, pay slips and listings into clean, verified data — the heart of AirCredit.
Berlin / Remote (EU) Full-time 3+ years ML in production €60,000 – 80,000 + equity
As a Machine Learning Engineer you'll own the models and pipelines with which AirCredit reads, classifies and translates financial documents into structured data fields. Your work decides how accurately and quickly a stack of paper becomes a bank-ready file.
You'll work closely with engineering, product and our mortgage experts, define the right quality metrics and take your models to production yourself — not throw them over the fence to another team.
What you'll do
- Build and improve models for document classification and data extraction (OCR, layout, NLP).
- Apply and fine-tune LLMs for extraction, plausibility checks and structured outputs.
- Build robust data and evaluation pipelines on real, messy documents.
- Own accuracy, latency and reliability in production.
- Care for privacy and security — we handle highly sensitive financial data in the EU.
What you bring
- More than 3 years of experience with machine learning in production systems.
- Strong Python skills and experience with modern ML frameworks (e.g. PyTorch).
- Hands‑on experience with NLP, LLMs or document/computer‑vision processing.
- A feel for solid evaluation over gut feeling — you measure before you claim.
- Good German and confident English.
Experience with OCR, layout models, RAG, MLOps or regulated industries like FinTech. Not required — curiosity and rigour count more.
What we offer
- Real impact: your models speed up thousands of financings and save real people weeks.
- Fair salary plus a share in the company's success (equity).
- Flexible remote‑first work within the EU with an office in Berlin.
- Access to real data and compute to actually make models better.
- 30 days of holiday and a team that shares ownership instead of micromanaging.
AirCredit is an equal‑opportunity employer. We welcome applications regardless of origin, gender, age, religion, disability or sexual identity.
#J-18808-Ljbffr
