Role Description Como especialista técnico, você supervisionará o ciclo de vida completo de modelos de alta criticidade, garantindo que eles suportem decisões de negócio precisas e de alto impacto. Sua missão é extrair o valor máximo desses modelos para tornar nossa estratégia de crédito a mais competitiva, justa e segura do mercado. - Liderança Técnica: Comandar o desenvolvimento, validação e monitoramento de modelos de ML de impacto direto no negócio. - Parceria Estratégica: Traduzir desafios complexos de negócio em soluções de Data Science acionáveis para as áreas de Crédito. - Otimização de Performance: Conduzir análises robustas de risco para identificar oportunidades de melhoria nos modelos em produção. - Arquitetura e Escalabilidade: Influenciar a definição da arquitetura de dados e ML, garantindo robustez tecnológica. - Gestão de Stakeholders: Comunicar resultados técnicos e recomendações estratégicas para líderes de forma clara e estruturada. - Autonomia e Visão Holística: Definir prioridades técnicas com foco total no "big picture" e no resultado final da organização. Qualifications - Experiência Sênior/Principal: Histórico comprovado no desenvolvimento de modelos de machine learning (ML) para processos críticos de decisão (preferencialmente em Finanças/Crédito). - Expertise Técnica: Profundo conhecimento em Python, SQL e ferramentas e algoritmos de machine learning. - Conhecimento de estatística clássica, teste de hipóteses e experimentação (por exemplo, inferência causal). - Visão Sistêmica e Operacionalização de Modelos: Capacidade de projetar soluções de ML que sejam escaláveis e robustas, atuando na definição de arquiteturas (como feature stores, model registries e pipelines automatizados) em parceria com times de engenharia. - Padronização e Governança: Experiência na criação de camadas de abstração e bibliotecas internas que encapsulam boas práticas e padronizam o ciclo de vida de desenvolvimento de modelos. - Cultura de Engenharia: Experiência prática com Git/GitHub em ambientes produtivos. - Resolução de Problemas: Fortes habilidades analíticas para diagnosticar riscos e propor soluções baseadas em dados. - Comunicação e Influência: Capacidade de apresentar análises complexas para públicos técnicos e executivos. - Idiomas: Inglês avançado (leitura e conversação). Requirements - Vivência em ambientes de MLOps e Data Warehousing moderno (Sagemaker, Vertex, MLflow, Athena, Redshift, BigQuery, Snowflake, …). - Arquitetura de ML em Escala: Histórico de desenho de arquiteturas de machine learning em nuvem que suportam múltiplos modelos em produção simultaneamente. - Construção do Zero: Experiência em estruturar áreas de ML do início, definindo desde a infraestrutura básica até os processos de desenvolvimento, validação e monitoramento. - Pós-graduação (Mestrado ou Doutorado) em áreas quantitativas. Benefits - Ambiente de crescimento e desafios. - Valorização da diversidade e inclusão em todas as nossas vagas.

• Build high performance ML models that improve credit predictability and customer outcomes. • Build end-to-end machine learning pipelines including data extraction, feature engineering, model building, performance evaluation, and implementation. • Build end-to-end model monitoring pipelines to monitor model performance, including model stability, drift detection, and performance diagnostics. • Develop and own reporting pipelines that support recurring risk reporting, monitoring, and ad-hoc analysis • Explore rich data assets to uncover trends, identify key risk drivers, and generate insights. • Define and monitor data quality metrics (completeness, accuracy, timeliness, consistency) • Manage full modeling lifecycle: model design, data preparation and exploration, feature engineering, model development, evaluation, deployment, monitoring and documentation. • Design experiments and challenger models to test new ideas and drive innovation. • Contribute to audit-ready documentation and support model validation and governance processes. • Leverage modern AI technology and tools to improve workflow, enhance modeling performance, establish and promote best practices. • Work cross-functionally to ensure models are explainable, transparent, and aligned with business goals and regulatory expectations. • Translate analytical findings into recommendations for Strategy, Pricing, and other business decisions. • Build pipelines that are scalable, automated, and well-documented.

Role Description Yassir is seeking a highly skilled and motivated Data Scientist to join our Artificial Intelligence (AI) team and contribute to some of our key projects, such as Personalization and Recommendation Engines. As a Data Scientist, you will play a crucial role in analyzing and modelling data to optimize our Machine Learning (ML) systems. Your expertise in both predictive modelling and software development will be essential in driving our solutions and providing value to Yassir. This is a very exciting opportunity, tackling some of Yassir’s most critical problems. Key Responsibilities - Become an expert point of contact and thought leader on your scope by mastering the details and principles pertaining to it. - Focus on Personalization and Recommendation Engines capabilities. - Identify and propose ML opportunities related to your scope and beyond. - Support with requirements definition and prioritization of ML projects. - Collaborate with cross-functional Engineering and Product teams. - Champion Data Quality as a critical input component to all ML solutions and Analytics. - Conduct Exploratory Data Analysis and subsequent Feature Selection / Engineering. - Utilize Statistical and ML techniques, as appropriate, for model training. - Validate and tune ML models. - Visualize analysis / modelling results focusing on meaningful, actionable metrics and insights. - Deploy and test ML applications using our MLOps infrastructure. - Monitor ML models on their technical performance, business impact and underlying data / concept drift. - Explain technical solutions in a business-friendly manner, supporting Product teams in their communications and reporting. - Maintain and improve technical documentation of delivered solutions. - Support the Data & AI domain in developing its technical capabilities, improving its ways of working and collaboration with other dependent teams. - Champion Data Culture, proactively share knowledge across teams, and participate and drive team building activities. Qualifications - Solid Mathematical / Statistical / Machine Learning as well as Software Development technical skills - supported by a Masters degree or above in a relevant quantitative field such as Mathematics, Statistics, Data Science, Machine Learning, Computer Science, Software Engineering. - Comfortable in efficient, production quality Python and SQL coding at a professional setting with at least 3 years of industry experience. - Comfortable with key software engineering concepts, such as code / memory profiling, code optimization, scalability, code / QA testing, cost optimization and associated best practices. - Prior experience with Personalisation and Evaluation related problems and/or modelling techniques. - Comfortable with key Statistical concepts, such as statistical testing and causal analysis. - Analytical thinking and problem solving skills. - Engineering mindset focused towards delivering robust applied data science solutions. - Visualization skills, including experience with common Python ecosystem libraries and/or Analytics / BI tooling. - Familiarity and prior use of Cloud solutions and their data / ML services - at Yassir we use Google Cloud Platform (GCP), experience with which is highly preferred. - Mastering of the end-to-end (ML) model development lifecycle. - Excellent communication skills, including presentation and oral / written communication (clear articulation, concise documentation) in professional English. - Positive attitude and resilience. - Strong interpersonal skills focused on peer support, empathy, active listening, team building and stakeholder relationships building. - Internal drive, self-motivation and ability to work independently including own effective project management. Nice to have - Experience with Delivery, Mobility or Financial Services companies. - Experience working on ML features for Digital Products (apps, websites).

For People is a team of skilled technologists improving government digital services for disadvantaged and vulnerable populations. We embed directly in government agencies to modernize software, systems, and platforms so that they better serve people. Your Impact You'll be a key hands-on contributor to a high-profile project with the Centers for Medicare & Medicaid Services (CMS) that impacts millions of people. We're working to transform a manual data process into an automated solution, and you will be at the heart of that technical work. Working alongside senior engineers and domain experts, you will write the core code and queries that bring this new system to life. Your daily contributions will help ensure that state governments receive accurate data, ultimately supporting the integrity of the Medicaid program for millions of Americans. Our Culture For People is a team of humans. We place a significant amount of emphasis on positive work-life balance, setting healthy expectations, and making sure our loved ones are taken care of first. That means picking a child up from school during the day or going for a mid-day walk is okay! This position is 100% remote. Our entire team is remote across the United States, from the West Coast to the East Coast. There will never be a return-to-office, as we have none! This position's published base salary range is between $100,000 and $120,000 annually, plus generous benefits (e.g., For People pays 100% of Gold-tier employee health insurance premiums) and annual company profit sharing. Your Opportunities At For People, you will: - Write and refine queries to analyze and extract information from government healthcare datasets, including T-MSIS. - Collaborate with data engineers to support the deployment and maintenance of automated pipelines within Databricks. - Work with the data team to translate policy requirements and business rules into reliable data transformations. - Help implement and monitor data quality tests to safeguard the accuracy and privacy of sensitive enrollee information (PHI). - Partner with business analysts and stakeholders to map out data requirements and maintain clear documentation. - Generate reports and data visualizations that communicate key insights back to CMS. You Bring - A humble and caring attitude aligning with For People’s values – how we work with passion, fun, curiosity, sustainability, humility, and respect - 3+ years of professional experience as a Data Scientist, Data Analyst, or similar role. - Solid proficiency in writing effective SQL to interact with and manipulate large datasets. - Strong programming skills in Python for data analysis, scripting, and automation. - Experience working with data pipelines and ETL processes in a modern cloud environment. - A deep curiosity and passion for untangling complex problems and a drive to see your work create a positive social impact. Prior exposure to healthcare, CMS, or state Medicaid data is a bonus. Experience with Databricks is a bonus as well.Additional Details You will be working on a United States government platform, and they have a few basic requirements for contractors like ourselves. You must perform all work physically within the United States at all times. In addition, you must be a United States citizen and be able to pass a government-performed public trust background check. For People is an Equal Employment Opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, age, disability, genetics, and/or veteran status.