• Deve ser capaz de tocar um projeto inteiro com quase zero supervisão • Desenhar e construir soluções matemáticas/estatísticas de acordo com as demandas das áreas de negócio • Desde a primeira reunião, desenhar o escopo do projeto junto da área de negócios • Traduzir a demanda em modelos estatísticos programáveis • Análise de prazos, trade-offs entre técnicas e necessidades do negócio • Programar todas as etapas do projeto (coleta análise dos dados, formatação para ingestão do modelo, modelagem, geração de outputs utilizáveis) • Guiar e ensinar qualquer parte do processo/ciclo de vida de um projeto de machine learning para os membros menos experientes • Criar e configurar intents, entities e fluxos conversacionais com LLMs • Desenvolver modelos estatísticos e matemáticos em python • Criar e manter projetos de ML com CI/CD • Implementar lógica de negócio e regras de decisão nos modelos • Garantir performance, escalabilidade e resiliência das integrações • Monitorar e otimizar o desempenho dos modelos criados • Auxiliar na mentoria dos membros menos experientes

Role Description Sr. Data Scientist for St. Louis, MO to: - Develop predictive agronomic models to address scientific challenges in precision agriculture. - Manage data preparation and cleansing for multi-source agronomic data. - Ensure quality standards & build reliable pipelines for integration and analysis. - Lead implementation of research projects using statistical, machine learning & optimization techniques. - Review & revise code to ensure quality and reproducibility. - Provide mentorship and technical guidance to junior data scientists. - Provide coaching & training in agile framework and methodologies. - Coordinate sprints, retrospective meetings & stand-ups. Qualifications - Master's in Data Science, Statistics, Applied Mathematics, or closely-related quantitative field. - 4 years experience building predictive machine learning, statistical models, and optimization algorithms for research applications. Requirements - Deploying code to AWS. - Writing code in Python with data science packages, including Pandas, Numpy & Geopandas for data aggregation. - Using Matplotlib & Seaborn for data analysis & visualization. - Using PyMC for Bayesian statistical modeling & inference. - Using Sklearn & XGboost for machine learning and modeling. - Using TensorFlow and Keras for deep learning modeling. - Working with large, complex datasets across agronomic, genetics, environmental & weather domains using SQL, PySpark and Google BigQuery. - Designing & analyzing agronomic trial data, including experimental protocols and hypothesis testing to evaluate outcomes. - Using version control systems, including GitLab, to track code history & perform code review. - Creating & deploying CI/CD pipelines, applying MLOps best practices, including code documentation, merge/pull requests, unit testing, and code modularization. - Using JIRA & Agile methodologies for task prioritization and project management. - Communicating with technical & non-technical stakeholders at all levels of the organization, including business stakeholders, agronomists, data engineers, and data scientists. Benefits - Salary Range: $120,000.00 to $150,000.00. - Additional compensation may include a bonus or commission (if relevant). - Health care, vision, dental, retirement, PTO, sick leave, etc.

• Set and own the data science strategy across simulation and synthetic data, ML evaluation (perception, prediction, planning), fleet operations analytics, and the data platform that supports them; translate that strategy into a 12–24 month roadmap with measurable milestones. • Lead, grow, and develop a team of senior data scientists, ML engineers, and front-line managers; recruit from a small expert pool, calibrate the bar, and build a hiring brand that allows May Mobility to win against AV, robotics, and AI competitors. • Partner with Engineering, Product, Safety, and Operations leaders to define release criteria, performance metrics, and ODD-expansion gates; use data to make the business case for what we deploy, where, and when. • Drive ML and analytics applications end-to-end: dataset curation, scenario coverage, modeling, offboard evaluation, productionization, and continuous monitoring of fleet performance in the wild. • Establish measurement and experimentation standards across the company — including before/after analyses for stack changes, A/B-style comparisons in simulation, and statistically credible reporting on real-world incidents. • Lead team-wide quality activities including design and code reviews; hold the bar on engineering rigor for production data science systems. • Track and trend technical performance of the autonomy stack in the field; surface root causes, prioritize fixes with engineering, and represent fleet-data findings to executives, regulators, and partners. • Provide technical guidance to Engineering and Operations leaders on issue diagnosis, resolution, and the ML changes most likely to move our key safety and service metrics. • Represent May Mobility's data science work externally where appropriate — through publications, conference talks, partner reviews, and recruiting.

• Develop research methods and data analysis plans related to healthcare utilization, cost trends, financial forecasting, member, and provider experience. • Expertly use appropriate software tools to retrieve, edit and tabulate data from various databases and files. • Conduct descriptive, prescriptive, predictive analyses. • Summarize complex data for leadership in the appropriate form (e.g., statistical summaries, narratives, charts, tables, graphs, etc.) to convey meaning, significance, and actionable information. • Contribute/Lead in the research and development of models, algorithms, and analysis tools to mature the use and creation of self-service data products at CareOregon. • Develop visual reporting (e.g., dashboards, scorecards, etc.) using data visualization tools such as Tableau when appropriate. • Develop appropriate subject matter, domain expertise and serve as an expert resource. • Collaborate with other subject matter experts to identify opportunities for building repeatable data products. • Collaborate with business teams to understand business needs and to illicit and document requirements for analytics, algorithms, models, etc. • Develop reporting tools to comply with regulatory reporting requirements. • Review and assess completeness, validity, and reliability of internal data used for analysis and reporting. • Create and maintain technical documentation such as data dictionaries, business glossaries, metric definitions, and other data resources. • Thoroughly document models, algorithms, data products, processes and any analysis, reports developed. • Contribute to, and actively participate in, community of practice to improve the skills and capabilities of other analysts at CareOregon. • Assist with, prepare, and/or deliver presentations to community groups, regulatory agencies, leadership, and other teams as needed.