Computer Vision Data Scientist, Receipt Fraud

TechBiz Global GmbH; Kiel; Vor Ort; EUR 50.000 - 75.000; Teilzeit

Zusammenfassung

A leading recruitment service provider is seeking a Computer Vision Data Scientist to join a client team in Kiel. The ideal candidate will have 4+ years of experience in data science with a focus on fraud detection and optimization of ML models. Responsibilities include analyzing receipt data for fraud patterns, developing statistical methods, and designing scoring systems. This is a part-time role with flexible hours and offers the chance to work with cutting-edge technologies in a global team.

Leistungen

Cutting-edge tech stack including GenAI and ML

Flexible remote work

Opportunity to influence product direction

Qualifikationen

• 4+ years as a data scientist with experience in fraud detection.
• Strong expertise in hypothesis testing and anomaly detection.
• Hands-on experience with classification and deep learning techniques.

Aufgaben

• Analyze large-scale receipt data for fraud patterns.
• Develop statistical methods to detect inconsistencies.
• Design feature engineering strategies combining OCR and visual embeddings.
• Build and optimize ML models for fraud detection.

Kenntnisse

Hypothesis testing

Time series analysis

Anomaly detection

Classification methods

Deep learning

Image processing

Tools

scikit-learn

XGBoost

PyTorch

TensorFlow

Jobbeschreibung

At TechBiz Global, we are providing recruitment service to our TOP clients from our portfolio. We are currently seeking an Computer Vision Data Scientist specialist to join one of our clients ' teams. If you're looking for an exciting opportunity to grow in a innovative environment, this could be the perfect fit for you.

Job Description :

1. Analyze large-scale receipt data for fraud patterns and anomalies.

2. Develop statistical methods to detect subtle inconsistencies in receipt data.

3. Design feature engineering strategies combining OCR, visual embeddings, and

behavioral signals.

4. Build and optimize ML models for fraud detection using collected data points.

5. Develop fraud scoring algorithms that combine multiple detection signals and model

outputs.

6. Implement threshold optimization strategies balancing precision and recall for different

risk levels.

7. Design comprehensive fraud scoring systems.

8. Develop weighted scoring mechanisms adaptive to fraud types and retailer patterns.

9. Create interpretable scoring frameworks for manual review teams.

4+ years as a data scientist with experience in fraud detection.

Strong expertise in hypothesis testing, time series, and anomaly detection.

Hands-on experience with classification, ensemble methods, and deep learning (scikit-learn, XGBoost, PyTorch / TensorFlow).

Computer Vision - Strong experience with image processing and embedding, specifically EfficientNet and FAISS, is a plus.

Experience with high-volume transaction processing and real-time decision systems.

Knowledge of retail / e-commerce fraud patterns preferred.

Familiarity with document fraud techniques and anti-fraud methodologies.

Part-time commitment with flexible hours

Why us?

• Cutting-edge tech stack including GenAI and ML
• A global team with diverse perspectives
• Flexible remote work
• Opportunity to influence product direction and company growth