Data Scientist (Mid-level) – Fraud Prevention

Role Overview

• Lead end-to-end Data Science projects, from problem definition and scoping with Product/Operations to production deployment, monitoring business impact and continuously evolving the solution.
• Design, implement and maintain Machine Learning pipelines in production (batch and online), ensuring reliability, scalability and maintainability in high-volume, low-latency scenarios.
• Manage the full model lifecycle (experimentation, validation, deployment, monitoring and iteration), including defining metrics and routines to track data drift and concept drift.
• Develop and enhance inference systems for various use cases (batch and real-time), making architectural trade-offs to support parallelization, concurrency and low latency.
• Optimize end-to-end performance of production solutions, addressing latency, throughput and compute resource usage, with a focus on fast responses and handling multiple concurrent requests.
• Establish and improve MLOps practices (infrastructure, deployment and observability), including model and artifact versioning, automated deployments and continuous performance and health monitoring in production.
• Collaborate with Engineering Tech Leads and Product Managers to design feasible solutions, align expectations, communicate results (technical and business) and enable production delivery of systems.
• Stay up to date with best practices in applied Data Science and development productivity (including AI-assisted development tools), evaluating and proposing improvements appropriate to the context and delivery quality.

Requirements

• Strong experience applying Machine Learning techniques and statistical modeling to business problems (e.g., regression, classification, time series).
• Proven experience deploying and maintaining machine learning models in production for both online and batch use cases.
• Proficiency in SQL, Python and Spark for manipulating and analyzing large datasets.
• Familiarity with code versioning practices (Git).
• Solid experience with MLOps frameworks (especially MLflow).
• Strong knowledge of Statistics, Statistical Inference and Hypothesis Testing (A/B testing).
• Bachelor’s degree or equivalent practical experience in Computer Science, Engineering, Statistics, Mathematics, Physics or related fields.

Tech Stack

• Python
• Spark
• SQL

Benefits

• Medical and dental insurance with no co-pay
• Life insurance
• Allowance for purchasing medications
• Subsidy for physical activity or gym membership
• Financial wellness support for the team
• 4 free monthly sessions with a therapist or nutritionist
• Flexible meal card
• Free meals at headquarters
• Childcare assistance
• Parental support program
• Extended maternity and paternity leave
• In-company training platform
• Education assistance covering 70% of tuition for degrees and language courses
• Work equipment provided
• Home office allowance
• Furniture allowance