Machine Learning Engineer Intern
hace 4 días
Madrid
WHAT YOU WILL BE DOING Envíe su solicitud a continuación después de leer todos los detalles y la información de apoyo sobre esta oportunidad de trabajo. You will join Getnet's AI Lab, driving the design, development, and production deployment of machine learning models and data-driven solutions across multiple geographies. You will work end-to-end: from exploratory analysis and model training to production-grade pipelines and monitoring. The role will be responsible for design, train, and deploy all kinds of ML models on Getnet data at scale. Build and maintain end-to-end ML pipelines from feature engineering through scoring and monitoring. Act as technical lead in the design and execution of proofs of concept and new AI/ML initiatives within Getnet Payments' AI Lab. Drive technical decision-making and collaborate with business and product teams to identify high-impact opportunities. Furthermore, contribute to code quality, documentation, and team best practices. Mentor junior team members and communicate technical results to non-technical stakeholders. WHAT WE ARE LOOKING FOR Skills & Knowledge: ~ Bachelor's or Master's degree in Computer Science, Mathematics, Statistics, Physics, Engineering, or a related quantitative field (PhD is a plus). Strong foundations in statistics, probability, and linear algebra applied to real-world ML problems. ~5+ years of professional experience in Machine Learning Engineering, Data Science, or Applied Research roles with a proven track record of deploying ML models to production in cloud environments. Background in fintech, payments, banking, or e-commerce is highly valued. ~ Strong proficiency in Python (pandas, NumPy, scikit-learn, XGBoost/LightGBM, SciPy, statsmodels) with solid experience building and deploying classification, regression, uplift, and anomaly detection models on tabular data at scale. Knowledge of feature engineering, temporal validation, explainability (XAI), and mathematical optimization. ~ Experience with observational causal inference (propensity scores, IPW, AIPW, meta-learners, Causal Forests), uplift modeling, A/B testing, and experimental design. Familiarity with libraries such as EconML, causalml, and DoWhy. ~ Proven experience deploying and operating ML models on Databricks (Workflows, Delta Lake, Unity Catalog, Databricks Connect) within Azure cloud (Azure Databricks, Azure OpenAI Service, AKS, Key Vault). Experience with PySpark/Spark SQL and MLflow end-to-end (experiment tracking, model registry, serving, versioning). ~ Experience with anomaly detection, change point detection, time series clustering, seasonality/trend analysis, and production model monitoring (drift detection, data quality alerts, performance dashboards). ~ Understanding of transformer-based architectures and LLM concepts. Familiarity with prompt engineering, integration of LLMs into ML pipelines, and operationalization of LLM-based solutions via Azure OpenAI or similar services. ~ Ability to write clean, testable, and well-documented Python code. Experience with Git, CI/CD for ML, automated testing (pytest), and schema validation. Experience working in agile, cross-functional teams across multiple markets or geographies. ~(Nice to have): Experience designing and deploying AI agents based on LLMs (LangChain, LangGraph, OpenAI Agents SDK, CrewAI, Agno). Familiarity with MCP, agent observability (LangFuse, MLflow Tracing), agentic patterns (multi-agent orchestration, RAG, tool use), and domain-specific (vertical) AI models for industry use cases. xcskxlj ~(Nice to have): Experience with AWS (SageMaker, S3, Bedrock, EKS, Lambda, Step Functions, Glue) and ability to work across multi-cloud environments (Azure + AWS).