Sr. Data Scientist

Key Skills

Apache Airflow, Apache Hive, AWS, Data science techniques, Google Cloud Platform (GCP), Machine learning techniques, Python Programming, PyTorch, Scikit-learn, Spark-SQL, SQL, TensorFlow, XGBoost

Job Description

About Us

At Viaduct, we are developing an end-to-end machine learning platform to empower automakers to build safer, more intelligent, and personalized vehicles. Our AI solution runs off of a patented TSI engine, which is a series of algorithms for detecting multivariate anomalies in time series data. The result is an AI solution that automatically finds complex multivariate relationships to uncover the signal in the noise of high dimensional data. Customer value lies in early issue detection by receiving early warning alerts to potential systematic issues, root cause analysis by triaging specific patterns that are causing failures in the field, VIN level predictive maintenance delivering personalized service recommendations to every vehicle on the road and data unification through viewing all relevant information in one place.

We are a diverse team motivated to solve the hardest problems in the automotive industry.

Who You Are

You are an experienced data scientist with a number of successfully completed data science projects under your belt. You are motivated by real-world problems and enjoy working with customers to solve their biggest challenges. You are excited by opportunities to deliver value by turning data science into actionable business and technology insights. Your ability to build relationships with customers and understand their needs ensures that your solutions are practical, scalable, and aligned with business objectives.

Position Responsibilities:

• Work with customers to understand their biggest challenges, gather requirements, and develop tailored data science solutions.
• Use advanced machine learning techniques and statistical analysis to transform complex datasets into actionable business insights. Communicate findings in a way that supports decision-making and strategic planning.
• Design and implement scalable data science models and workflows that can be deployed in real-world environments.
• Present data-driven insights and technical solutions to non-technical stakeholders, ensuring clear understanding of how the models and analytics add value to the business.
• Work cross-functionally with internal teams such as customer success, analytics, engineering, and product to ensure that data science solutions are seamlessly integrated into the broader technology stack.
• Work closely with customer success and solution delivery teams to bring modern data science to bear in order to solve a customer’s business problems

Expected Skills

• Strong machine learning and statistical analysis skills
• Comfort working side-by-side with customers
• Comfort working cross-functionally in a team-first and fast-paced environment
• Strong presentation skills communicating technical concepts to non-technical audiences
• Familiarity with working on datasets that don't fit within a single machine
• Self-motivated and able to work independently
• Excellent spoken and written communication skills
• Minimum of advanced degree (M.S. or Ph.D.) in a data science-related field or bachelors degree (B.Sc.) in a data science-related field coupled with exceptional track record of data science execution
• 5+ years of experience in a related field
• Proficiency in Python and SQL
• Hands on experience with ML libraries (scikit-learn, xgboost, MLlib, etc.)
• Familiarity with deep learning libraries (Tensorflow, Keras, PyTorch, etc.)
• Working knowledge of distributed/cloud compute platforms (AWS, Hive, Spark, Airflow, etc.)

Security and Privacy responsibilities

• Follow our policy and procedure documents related to security and privacy
• Follow the guidelines in the Employee Handbook
• Participate in new hire and annual training for security and privacy
• Treat data security and privacy as one of your primary job responsibilities
• Report Security Incidents you discover as bugs
• Get approval from the Security Team before adding new 3rd party software to our codebase
• Explicitly consider security implications when doing PR reviews

About the Role

Day 5

• Learn about Viaduct’s history and mission
• Get to know every team member
• Set up your development environment
• Understand Viaduct’s ML pipeline and data science workflow
• Learn about our current partners, their biggest needs, and the gaps they're looking for us to fill

Day 30

• Join multiple customer meetings
• Present your first deliverables internally
• Start planning for Viaduct’s future modeling needs
• Promote models to production
• Present your work at our weekly ML lunch

Day 90

• Meet with our customers in person
• Build new models at the forefront of machine learning
• Collaborate with engineers on improvements to data science tooling
• Present your models and relevant metrics to clients