At Allstate, great things happen when our people work together to protect families and their belongings from life’s uncertainties. And for more than 90 years our innovative drive has kept us a step ahead of our customers’ evolving needs. From advocating for seat belts, air bags and graduated driving laws, to being an industry leader in pricing sophistication, telematics, and, more recently, device and identity protection. Job Description This role is responsible for leading the use of data to make decisions. This includes: the development and recommendation of new machine learning predictive modeling algorithms, the coding/development of tools that use machine learning/predictive modeling to make business decisions, searching for and integrating new data (both internal and external) that improves our modeling and machine learning results (and ultimately our decisions), and discovery of new business problems that can be solved through the use of machine learning/predictive modeling. The role is responsible for assisting in the recruitment, selection, mentorship and development of junior data scientists. This role will also begin to manage projects of medium to high complexity. Arity Founded by The Allstate Corporation in 2016, Arity is a data and analytics company focused on improving transportation. We collect and analyze enormous amounts of data, using predictive analytics to build solutions with a single goal in mind: to make transportation smarter, safer, and more useful for everyone. At the heart of that mission are the people that work here-the dreamers, doers and difference-makers that call this place home. As part of that team, your work will showcase both your intelligence and your creativity as you tackle real-world problems and put your talents towards transforming transportation. That’s because at Arity, we believe work and life shouldn’t be at odds with one another. After all, we know that your unique qualities give you a unique perspective. We don’t just want you to see yourself here. We want you to be yourself here. Arity is committed to supporting an inclusive and diverse environment where you can thrive and learn from others. The Team At Arity, our Geospatial Data Science team is a fundamental and key differentiating component of Arity’s strategic vision, making transportation smarter, safer, and more useful for everyone. Not only do we know how to analyze and find meaning within billions of miles of driving data collected from smartphones, onboard devices and third parties, but we are passionate about how it affects the end-users of our products. On our team, people get the opportunity to build scalable distributed machine learning models to efficiently extract innovative insights from raw GPS and contextual data, enhance applications from enriched geospatial layers on a large scale, and create eye-opening data visualization. By leveraging our state-of-the-art algorithms, cost-effective platform, and easily accessible micro-services, we can quickly turn geospatial data into actionable insights. This team is also fully integrated within a cross-functional scrum team including product owners, software engineers, and other talents to collaborate with for creating innovative products. The Role As a machine learning scientist at Arity, you will lead the development of machine learning algorithms primarily on geospatial data. You are expected to make key technical decisions about how to implement machine learning models including both traditional and deep learning models on large volume of geospatial data. You have chances to influence the business for the entire cycle of the ML solution including data collection, processing, aggregation, modeling, and visualization. You will personally prototype the solution development for these projects and work with product owners, data/software engineers, and other partners for productionization and client delivery. Some example projects include: Efficiently route match raw GPS data Extract mobility patterns from users Derive driving behavior based on driving environment Build nationwide map quantifying road risk using telematics data Dynamic traffic volume forecasting Generate synthetic trips These geospatial insights help us understand transportation and the risk of behaviors on the road. You will also help shape and grow our culture we have worked hard to establish – promoting recognition of good work, continuous learning, winning together, and having fun along the way. Responsibilities Your day-to-day looks like: Working with large geospatial data sets using distributed computing frameworks Building spatial and machine learning models using a variety of libraries/tools and cutting-edge techniques Identifying opportunities for new machine learning solutions, exploring new data sources for enrichment, collecting appropriate labels for learning, establishing actionable metrics, and creating reusable model validations and risk mitigation Communicating results to key stakeholders in a clear and compelling manner Applying appropriate methodologies for the problem and validating the solution with the appropriate metrics Establishing and following data science best practices including peer review, code review, documentation, coding standards, and ensuring reproducibility and compliance Expanding your machine learning skillset through development opportunities and researching innovative tools and techniques to level up our capabilities Qualifications Successful candidates typically have: Master’s or PhD degree in a machine learning/AI related field such as engineering, statistics, computer science, physics, or related discipline Over 7 years’ experience with developing end-to-end machine learning solutions/algorithms including model development, model deployment, model monitoring, and model life-cycle management Demonstrated advanced knowledge in predictive models such as parameterized methods, ensemble algorithms, deep neural network, large language models, graph neural networks (GNNs), convolutional networks, transformer architectures Experience with scientific computing libraries Scikit-learn, TensorFlow, PyTorch, Spark ML-lib Experience with deploying ML models using AI platforms such as Vertex AI and Sagemaker Experience with geospatial data is highly preferred, such as US census data, weather data, parcel data, POI, etc Ability to process, analyze, and visualize large amounts of geospatial data using Spark/SQL is a plus Ability to translate product requirement into well-defined analytical problems Ability to provide written and oral interpretation of highly specialized terms and data, and ability to present this data to others with different levels of expertise Optional: Domain knowledge with transportation models Experience with spatial models and techniques such as kriging, spatial linear mixed models, spatio-temporal models, graph theory models Experience with image data Experience with large language models Supervisory Responsibilities This job does not have supervisory duties. Skills Algorithms, Artificial Intelligence Markup Language, Business Model Development, Data Analytics, Data Science, Deep Learning, Digital Literacy, Learning Agility, Machine Learning, Neural Networks, Predictive Analytics, Predictive Modeling, Results-Oriented Compensation Compensation offered for this role is $121,600 – 206,650 annually and is based on experience and qualifications. The candidate(s) offered this position will be required to submit to a background investigation, which includes a drug screen. Joining our team isn’t just a job – it’s an opportunity. One that takes your skills and pushes them to the next level. One that encourages you to challenge the status quo. And one where you can impact the future for the greater good. You’ll do all this in a flexible environment that embraces connection and belonging. And with the recognition of several inclusivity and diversity awards, we’ve proven that Allstate empowers everyone to lead, drive change and give back where they work and live. Good Hands. Greater Together. Allstate generally does not sponsor individuals for employment-based visas for this position. Effective July 1, 2014, under Indiana House Enrolled Act (HEA) 1242, it is against public policy of the State of Indiana and a discriminatory practice for an employer to discriminate against a prospective employee on the basis of status as a veteran by refusing to employ an applicant on the basis that they are a veteran of the armed forces of the United States, a member of the Indiana National Guard or a member of a reserve component. For jobs in San Francisco, please click “here” for information regarding the San Francisco Fair Chance Ordinance. For jobs in Los Angeles, please click “here” for information regarding the Los Angeles Fair Chance Initiative for Hiring Ordinance. To view the “EEO is the Law” poster click “here”. This poster provides information concerning the laws and procedures for filing complaints of violations of the laws with the Office of Federal Contract Compliance Programs To view the FMLA poster, click “here”. This poster summarizing the major provisions of the Family and Medical Leave Act (FMLA) and telling employees how to file a complaint. It is the Company’s policy to employ the best qualified individuals available for all jobs. Therefore, any discriminatory action taken on account of an employee’s ancestry, age, color, disability, genetic information, gender, gender identity, gender expression, sexual and reproductive health decision, marital status, medical condition, military or veteran status, national origin, race (include traits historically associated with race, including, but not limited to, hair texture and protective hairstyles), religion (including religious dress), sex, or sexual orientation that adversely affects an employee’s terms or conditions of employment is prohibited. This policy applies to all aspects of the employment relationship, including, but not limited to, hiring, training, salary administration, promotion, job assignment, benefits, discipline, and separation of employment.
Results-oriented deep-learning Data Analyst Artificial intelligence (AI) Data Science Machine Learning distributed-programming neural-network algorithms Quick learner