Data Scientist / MLE (Fraud & Payments)

Uplers
United States
4 days ago
Apply on arc.dev
Prepare application

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience required
0 years minimum
Working hours
Regular working hours
Job source

Tech stack

Application Programming Interfaces (APIs) Artificial Intelligence Data Analysis Cloud Database Cluster Analysis Continuous Integration Data Control Data Structures Data Visualization Fraud Prevention and Detection Data Intelligence Python (Programming Language)
+27 more
Machine Learning NoSQL NumPy Performance Tuning OpenAI Tensorflow Shopify SQL Databases Feature Store Feature Engineering Pytorch LangChain Retrieval-Augmented Generation Delivery Pipeline Large Language Models Deep Learning Git Pandas Build Management Scikit Learn HuggingFace Plotly Machine Learning Operations Api Design GPT User Identification Docker

Job description

Deep Learning, E-commerce/Shopify Domain., Data Scientist, Machine Learning, ML, Applied Scientist, Fraud Data Scientist, Payments, Transaction fraud, fraud detection, fraud prevention, Transaction risk, Chargeback, Python, Scikit-learn, PyTorch, TensorFlow, SQL, pandas, OpenAI, LangChain, Hugging Face, LLM, rag, payment, Financial Services, Fintech, MLOps, Production ml

An AI-powered fraud prevention platform is Looking for:

Data Scientist / MLE (Fraud & Payments)

About PA

PA is a Shopify-native return-fraud and order-risk decisioning platform that reinvents the post-purchase experience for retailers. We help merchants catch return abuse, empty-box (FTID) fraud, claim abuse, and payment fraud in real time - making high-stakes approve/decline decisions on live order and return traffic. By identifying and preventing abusive behaviour while rewarding loyal customers, we turn returns from a cost centre into a driver of loyalty and profit., Weβ€™β€˜re looking for a hands-on Data Scientist / MLE to help us build and deploy intelligent data systems. Youβ€™β€˜ll work closely with the Head of Machine Learning to clean, analyse, and model data, and to operationalise models and customer datasets in production.

Prior experience working in payment fraud or the payments domain is a must - you should already be comfortable with the data, risk signals, and problem patterns that come from fraud and transactional environments.

Our core work lies at the intersection of data intelligence, risk modelling, and identity resolution. Youβ€™β€˜ll build machine-learning systems that understand user, order, and return behaviour across digital commerce, working on problems like:

  • Identity Resolution: Connecting entities and related data points into unified customer identities.
  • Data Segregation and Clustering: Cleaning, parsing, and geo-clustering data to reveal underlying structure.
  • Abuse and Fraud Detection: Modelling behavioural and transactional risk signals to detect fraudulent activity.
  • Anomaly Detection and Scoring Pipelines: Identifying irregular patterns across large customer datasets.
  • Operational ML Systems: Deploying scoring APIs, automated feature stores, and monitoring pipelines at scale.

What Youβ€™β€˜ll Do

  • Perform data analysis, feature engineering, and exploratory insights across business datasets.
  • Build and deploy ML models (classification, regression, ranking, anomaly detection, etc.).
  • Fine-tune and integrate LLMs (OpenAI, Hugging Face, LangChain, RAG pipelines).
  • Support model deployment in cloud / API environments (Docker, GCP).
  • Create dashboards, reports, and validation pipelines for model and data monitoring.
  • Collaborate with engineering on scalable data workflows and inference pipelines.

Requirements

  • Hands-on experience in payment fraud or the payments domain is required - including exposure to transactional risk signals, fraud detection, or related risk-modelling work.
  • Python (NumPy, Pandas, Scikit-learn, TensorFlow or PyTorch).
  • Experience with LLM frameworks (Hugging Face, LangChain, OpenAI API).
  • Basic knowledge of MLOps (Docker, CI/CD, API serving, Git).
  • SQL / NoSQL data querying familiarity with cloud data environments.
  • Strong analytical mindset comfortable with statistics and data visualisation (e.g., Plotly, Seaborn).
  • Curious, pragmatic problem solver who enjoys taking models from notebook to production.
  • Able to learn quickly and adapt in a fast-moving AI environment.

Nice to Have

  • Exposure to RAG, prompt-tuning, or lightweight model fine-tuning.
  • Understanding of model monitoring and data drift detection.
  • Understanding of deep learning and graph data structures.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on arc.dev
Prepare application

Good distractions

Loading talks and stories from around this role…