Principal Machine Learning Engineer (P5)
- Role
- AI / ML
- Experience
- Lead
- Employment
- Full-time
- Company size
- Mid-size
Open to US, CA only. Set where you work from to check your eligibility.
No BS summary
Principal ML Engineer (P5) with 8+ years of experience in large datasets and statistical programming (Spark, R, Python preferred), and 10+ years with database software (RedShift, Hive, SQL, MYSQL). Must have 5+ years deploying cloud-based automated analytic processes and 5+ years in ML model deployment with automated monitoring. Master's degree required. Role involves understanding vehicle pricing, predicting future values, building/deploying ML models and ETL pipelines in AWS/Snowflake, and developing monitoring tools. Must be proficient in Python and SQL, and familiar with ML evaluation metrics. Experience with automotive market data is a plus.
Core skills
Required skills
Optional skills
Welcome to JD Power Careers! JD Power is a proven leader in business-critical data and intelligence to drive auto-related decisions with confidence and clarity. By leveraging unmatched proprietary data, advanced analytics and deep industry expertise, JD Power fuels original equipment manufacturers, retailers, lenders, insurers and partners to enhance their performance. Since 1968, JD Power has delivered incisive guidance and intelligence about customer interactions with brands and products. To learn more about the company, visit JDPower.com.
What you'll do
- Understand the features that drive the price of a vehicle and predict what future vehicle values will be.
- Utilize the latest technologies to solve challenging problems with data.
- Create innovative machine learning and ETL processes from the ground up.
- Deploy them into production in AWS and/or Snowflake.
- Develop cutting-edge tools for monitoring ML models.
- Deploy and monitor data pipelines and models that directly impact core products for clients.
- Experience daily immersion in automotive industry data.
- Collaborate with data science and engineering teams to build and maintain model training and forecasting/prediction ETL pipelines with appropriate data mappings, anomaly detection, feature engineering, and data imputation strategies.
- Deploy models and ETL pipelines in a reusable framework to generate predictions or forecasts for use in existing and net-new products.
- Lead the creation of model and data drift monitoring pipelines and reporting.
- Communications of technical topics to both lay and technical business stakeholders, product, and senior data science leadership while requiring minimal feedback for communication documents and presentations.
- Leads quarterly planning for major ML deployment projects with minimal supervision.
- Fluent in other data science models, data sources, and data limitations across business units.
- Collaborate with a variety of technical and non-technical teams, including data science, data engineering, data visualization, product, and automotive consulting teams.
What they require
- Passion for solving complex business problems with data.
- Curiosity to dig into complex datasets and codebases to identify anomalies and issues.
- Ability to lead the production and deployment of ML models and relevant input ETL pipelines end-to-end (especially large processes with many moving parts).
- Demonstrated proficiency in Python and SQL.
- Demonstrated use of ML evaluation metrics including accuracy, precision, recall, ROC, AUC, F1 scores, MSE, R-squared, etc., in model building & evaluation.
- Focuses on designing innovative solutions for challenging ML problems.
- Requires effective collaboration with stakeholders for ML adoption and best practices.
- 8+ years of professional experience working with large datasets.
- 8+ years of professional experience with statistical programming software (Spark, R, Python preferred).
- 10+ years of professional experience with database software (RedShift, Hive, SQL, MYSQL).
- 5+ years of professional experience deploying cloud-based automated analytic processes.
- 5+ in machine learning model deployment with automate model monitoring.
- Master’s Degree in Statistics, Data Science, Economics, Computer Science, or a related field.
- Enthusiasm for the automotive industry.
Benefits
- JD Power is committed to employing a diverse workforce. Qualified applicants will receive consideration without regard to race , color , religion , sex , national origin , age , sexual orientation , gender identity , gender expression , veteran status , or disability .
- Should you require accommodations during the recruitment and selection process , please reach out to tarecruitment@jdpa.com .
null
What people say about this company
3.4/ 5