Navigate Change
Data Scientist
Location
Brazil
Posted
12 days ago
Salary
0
Seniority
Senior
Job Description
Data Scientist
CI&T
• Desenvolvimento de Modelos Preditivos: Desenvolver modelos de propensão a default utilizando técnicas de ML tradicional (classificação binária, modelos ensemble como Random Forest, Gradient Boosting e equivalentes), com foco em precisão, recall e estabilidade em produção. • Seleção e Engenharia de Features: Conduzir análise exploratória de dados (EDA), identificar e selecionar variáveis relevantes a partir de dados contratuais estruturados e, progressivamente, incorporar variáveis externas (clima, safra, cenário macroeconômico, dados de recuperação judicial e fontes de notícias). • Experimentação no Databricks: Desenvolver e versionar experimentos de modelagem utilizando Databricks e MLflow, garantindo rastreabilidade de runs, parâmetros, métricas e artefatos de modelos ao longo dos ciclos iterativos. • Validação e Avaliação de Modelos: Projetar e executar estratégias robustas de validação (cross-validation, backtesting temporal, análise de estabilidade de score) garantindo que os modelos performem de forma confiável em janelas de projeção crescentes (3, 6 e 12 meses). • Ciclos Iterativos de Melhoria: Participar ativamente dos ciclos iterativos de refinamento do modelo — a cada sprint, incorporar novas variáveis, reavaliar performance e documentar aprendizados na Base de Conhecimento do programa. • Colaboração com Engenharia de Dados: Trabalhar em estreita parceria com os Data Engineers para garantir que os pipelines de dados alimentem corretamente os modelos, e que as saídas dos modelos (scores, projeções, alertas) sejam disponibilizadas nas camadas corretas da plataforma. • Comunicação de Resultados: Traduzir resultados técnicos dos modelos para linguagem de negócio, apoiando o Data Strategist na comunicação com stakeholders do cliente (superintendências, crédito, liderança). • Documentação Técnica: Documentar metodologias, decisões de modelagem e resultados em formatos estruturados que alimentem a Base de Conhecimento e possam ser consumidos por agentes de IA em fases subsequentes. • Monitoramento em Produção: Acompanhar a performance dos modelos em produção, identificar desvios de distribuição (data drift, concept drift) e propor ações corretivas ou re-treinamentos.
Job Requirements
- Experiência sólida em ciência de dados com foco em modelagem preditiva para problemas de negócio em produção
- Experiência comprovada com modelos de classificação e ensemble (Random Forest, Gradient Boosting, XGBoost ou equivalentes) em contextos de crédito, risco ou detecção de anomalias
- Experiência com Databricks para desenvolvimento, experimentação e versionamento de modelos (Delta Lake, MLflow, Spark MLlib ou bibliotecas equivalentes em ambiente distribuído)
- Sólido domínio de seleção de features, tratamento de dados desbalanceados e estratégias de validação temporal para modelos de risco
- Experiência em análise e modelagem de dados no ecossistema AWS (S3, Athena, SageMaker ou serviços equivalentes de ML gerenciado em nuvem)
- Capacidade de comunicar resultados e limitações de modelos para audiências não técnicas, com clareza e orientação para decisão de negócio
- Experiência no setor de serviços financeiros (crédito, risco, inadimplência ou similares)
Benefits
- Plano de saúde e odontológico;
- Vale alimentação e refeição;
- Auxílio-creche;
- Licença parental estendida;
- Parceria com academias e profissionais de saúde e bem-estar via Wellhub (Gympass) TotalPass;
- Participação nos Lucros e Resultados (PLR);
- Seguro de Vida;
- Plataforma de aprendizagem contínua (CI&T University);
- Clube de descontos;
- Plataforma online gratuita dedicada à promoção da saúde física, mental e bem-estar;
- Curso gestante e parentalidade responsável;
- Parceria com plataformas de cursos online;
- Plataforma para aprendizagem de idiomas;
- E muitos outros
Related Guides
Related Categories
Related Job Pages
More Data Scientist Jobs
GTM Insights & Analytics Lead
WrapbookWrapbook is a smart, intuitive platform that makes production payroll and accounting easier, faster, and more secure.
• Build and maintain the core BI dashboard suite that gives Sales and Marketing self-serve, real-time visibility into pipeline health, funnel conversion, segment-level coverage, campaign contribution, rep attainment, and loss analysis. • Own the GTM data dictionary — metric definitions, filter logic, and calculation rules — and maintain it as the authoritative source of truth across Marketing, Sales, and Finance. • Own the analytical layer of the GTM forecast process: historical conversion rates, pipeline coverage analysis, stage-weighted modeling, and forecast variance diagnosis. • Lead annual bookings planning analysis — historical win rates, segment-level capacity modeling, coverage assessments, and quota calibration inputs — and partner with Strategic Finance on revenue forecasting and GTM investment analysis. • Build scenario models for pricing, segmentation, and GTM structure decisions as needed by RevOps and Sales leadership. • Track campaign performance relative to pipeline contribution goals by segment; surface what's generating pipeline, what isn't, and where investment is misallocated. • Partner with Analytics Engineering to ensure GTM data from Salesforce, Marketo, and adjacent systems is correctly modeled in the data warehouse — flag gaps, validate logic, and escalate data quality issues. • Lead ad-hoc analytical projects supporting key company initiatives: segmentation analysis, market sizing, cohort analysis, win/loss diagnostics, and product-GTM intersection analysis.
• Develop, implement, and maintain machine learning and statistical models to support mission and program objectives • Analyze large structured and unstructured datasets to identify trends, anomalies, and actionable insights • Apply predictive analytics, classification, and regression techniques to real-world operational problems • Build and optimize data pipelines, ETL processes, and feature engineering workflows • Develop data visualization dashboards and reporting tools to communicate findings to technical and non-technical stakeholders • Work with cloud or on-premise environments to deploy scalable data solutions • Support test, evaluation, and analysis efforts for aviation, weapons systems, or mission systems programs • Provide data-driven recommendations to engineering teams, program managers, and government stakeholders • Interface with cross-functional teams including systems engineers, software developers, and analysts • Collaborate across IPTs to translate mission requirements into analytical solutions • Document methodologies, models, and results in accordance with DoD and program standards • Present findings to stakeholders in a clear and concise manner
Role Description Saalex is seeking a highly motivated Data Scientist to support mission-critical programs at China Lake. This role will focus on developing and deploying advanced analytical models, supporting test and evaluation efforts, and transforming complex datasets into actionable insights for engineering, operational, and leadership teams. Essential Functions - Data Analysis & Modeling - Develop, implement, and maintain machine learning and statistical models to support mission and program objectives. - Analyze large structured and unstructured datasets to identify trends, anomalies, and actionable insights. - Apply predictive analytics, classification, and regression techniques to real-world operational problems. - Technical Development - Build and optimize data pipelines, ETL processes, and feature engineering workflows. - Develop data visualization dashboards and reporting tools to communicate findings to technical and non-technical stakeholders. - Work with cloud or on-premise environments to deploy scalable data solutions. - Mission & Program Support - Support test, evaluation, and analysis efforts for aviation, weapons systems, or mission systems programs. - Provide data-driven recommendations to engineering teams, program managers, and government stakeholders. - Interface with cross-functional teams including systems engineers, software developers, and analysts. - Collaboration & Documentation - Collaborate across IPTs to translate mission requirements into analytical solutions. - Document methodologies, models, and results in accordance with DoD and program standards. - Present findings to stakeholders in a clear and concise manner. Qualifications - Experience supporting DoD, aerospace, or government programs strongly preferred. Requirements - Technical Skills: - Advanced proficiency in Python (NumPy, Pandas, Scikit-learn, TensorFlow, PyTorch). - Strong experience with SQL and relational databases. - Experience with data visualization tools (Power BI, Tableau, Matplotlib, Seaborn). - Solid understanding of machine learning techniques (classification, regression, clustering, NLP, etc.). - Data Engineering & Systems: - Experience building data pipelines and ETL processes. - Familiarity with cloud platforms (AWS, Azure, or similar) or on-prem DoD environments. - Understanding of data architecture and large-scale data processing. - Analytical Skills: - Strong statistical analysis and modeling experience. - Ability to translate complex data into actionable insights. - Demonstrated problem-solving skills in ambiguous or evolving environments. - Collaboration & Communication: - Ability to work effectively within cross-functional teams and IPT structures. - Strong verbal and written communication skills. - Experience briefing technical and non-technical stakeholders. Education - Bachelor's degree in Computer Science, Software Engineering, Information Technology, or related technical field, or equivalent practical experience required. Security Clearance - Active Secret Clearance required. Requirements to obtain a clearance include US Citizenship, security investigation, etc. Benefits - Health Care Plan (Medical, Dental & Vision). - Retirement Plan (401k, IRA). - Life Insurance (Basic, Voluntary & AD&D). - Paid Time Off (Vacation, Sick & Public Holidays). - Short Term & Long Term Disability. - Training & Development. - Wellness Resources. - Stock Option Plan.
Role Description UPMC Health Plan is hiring a Sr. Data Scientist to join the Artificial Intelligence team! This role may work fully remotely and must reside within the United States. The Senior Data Scientist develops, implements, and monitors advanced analytic, medical informatics, and predictive modeling tools for healthcare programs. - Design, develop, and implement health care analytic and biomedical modeling programs. - Converse with and provide guidance on the selection and use of modeling software and programs. - Serve as a consultant to ensure coordination in systems planning, development, and implementation between utilization management and other areas needing reporting, development, information systems, and external organizations. - Implement plans for capturing and creating new data elements to support department needs. - Define methodologies for reporting and evaluate software requirements needed to support analytic reporting. - Identify staffing needs to enhance modeling and reporting abilities and participate in recruitment. - Collaborate with Health Plan and Health System data scientists, as needed. - Lead the development and deployment of advanced machine learning models. - Oversee the end-to-end data science process, from data collection to model deployment. - Mentor and guide junior data scientists and analysts. - Collaborate with senior leadership to identify and prioritize data science projects. - Communicate complex technical concepts to non-technical stakeholders. - If needed, create and/or maintain documentation of a data dictionary to ensure that data is used efficiently and effectively, to help promote better data governance, improve data quality, & enhance data management processes. Qualifications - Ph.D. or Masters degree in data science, Statistics, Computer Science, or a related field with 4 years of relevant experience OR a Bachelor's degree with 7 years of relevant experience. - At least 2 years post terminal degree strongly preferred. - Extensive experience in data science and machine learning. - Strong programming skills in Python, SQL, and other relevant languages. - Experience conducting bias and segmentation analysis preferred. - Experience in the health care industry is a bonus. - Proven ability to lead and manage data science projects. - Excellent communication and leadership skills. - Strong expertise building and deploying models on Azure cloud framework or other cloud frameworks. - Preferred skills include using Transformers, Large Language models, GenAI, or AI Agents. Licensure, Certifications, and Clearances - UPMC is an Equal Opportunity Employer/Disability/Veteran


