Who We Are:
With industry-leading Electronic Logging Device (ELD) hardware and Fleet management platform- KeepTruckin is bringing the trucking industry online and fundamentally changing the way freight is moved on our roads.
About the job:
We’re looking for passionate engineers to work on KeepTruckin’s Data and Machine Learning Platform. As an early member of our team, you will spearhead KeepTrucking’s efforts to organize and use petabyte-scale telematics, vehicle data, videos and various customer and derived data through efficient storage, transformation, retrieval, modeling and serving.
- Own KeepTruckin’s data pipeline and processing flow maintaining reliability, scalability and performance
- Design and implement data models and schema based on engineering and business needs
- Set up workflows and ETL infrastructure with tooling to enable self-serve data processing
- Build platform for machine learning model training, batch evaluation, automated re-training, continuous monitoring and deployment in a micro-service architecture
- Build visibility into machine learning and system performance and optimize if necessary
- 4+ years experience in data engineering and building machine learning platforms
- Extensive experience with Hadoop tools such as HDFS, Hive, Presto, Parquet or similar technology
- Expertise in data-oriented programming such as Spark, Python, Map-Reduce, SQL with solid understanding of query performance and tuning
- Experience with workflow management tools such as Airflow, AWS Batch, Luigi or similar technology
- Familiarity with machine learning libraries like xgboost, pyTorch, tensorflow, Keras, Caffe2, scikit-learn, H2O
- Knowledge of Amazon Web Services is a big plus
AWS, scikit-learn, SQL, Python, and Engineering
about 1 month ago - source
No longer accepting applications.