Customer Job
Applied Scientist III
Job ID : 24-03750
Pay rate range - $75 / hr. to $79 / hr. on W2
Remote
PST local
Must Have
Deploying ML models
Python
Qualifications
- Bachelor's or Master’s degree in an analytically rigorous field (Data Science, Statistics, Computer Science, Industrial Engineering, Econometrics).
- Experience as an ML engineer or data scientist role building and deploying ML models on the cloud.
- Experience writing code in Python and SQL, or similar, with documentation for efficient knowledge sharing and reproducibility.
- Demonstrable track record of dealing well with ambiguity, prioritizing needs, and delivering results in a dynamic environment.
- Excellent communication skills with the ability to explain complex technical concepts to non-technical audiences, while also efficiently interacting with deeply technical peers.
- Knowledge of AWS (e.g. Athena, Sagemaker, S3, EC2, RDS).
Leadership Principles
- Deliver results
- Bias for action
- insist on high standards
Typical Tasks
Develop a new ticket classification model using labeled, historical data
Collaborate with internal teams to define model requirements, gather data, and interpret results.
Implement a robust model testing regime to validate the effectiveness against predefined accuracy metrics.
Establish and oversee a continuous improvement strategy for the classification model, including regular data benchmarking and revision schedules.
Work closely with technical and non-technical stakeholders to ensure the model aligns with business needs and compliance standards.
Provide expertise in machine learning and predictive modeling to optimize the performance of the classification system.
Document all phases of model development and provide training and support to internal teams on utilizing the new system.
Job Description
We are seeking an experienced Data Science Contractor to lead the development and implementation of a new trouble ticket classification model.
This role involves collaborating closely with cross-functional teams and external partners to design, test, and deploy an advanced model that meets the strategic objectives of improved accuracy and performance in automated ticket classification.