TypeScriptMachine LearningNatural Language ProcessingData Engineering
About this role
Role Overview
Establish a development framework consisting of task breakouts, milestones, deliverables, and risk mitigation strategies for the proof-of-concept.
Participate in discussions involving current intake workflows, decision-making processes, and the allocation of State labor resources.
Contribute to the identification of intake process shortcomings and prioritize them based on their impact on children and State resources.
Lead the development of a new intake process that leverages natural language processing and machine learning algorithms.
Evaluate architectural, computational, and data source trade-offs for each functional block, considering technical, schedule, and security risk factors.
Create and lead the design review process, evaluating functional design, risk factors, data sources, and proposed methods of demonstration.
Oversee prototype implementation through weekly status updates and gate reviews, providing guidance to mitigate risk and remove roadblocks.
Provide conference room demonstration support over 3 to 4 days, showcasing how the prototype application can improve child outcomes and reduce State resource usage.
Capture key stakeholder feedback on technical aspects of the application during the demonstration phase.
Contribute to the development of a roadmap for integrating the developed technology into the State's existing ecosystem of technologies and processes.
Requirements
Minimum Qualifications Bachelor's, Master's, or Ph.D. in computer science, mathematics, engineering, physics, or a related field.
Prior participation in U.S. Federal Government data science programs requiring TS/SCI clearance, delivering solutions that combine geospatial disciplines, pattern of life analysis, and social network connections.
Demonstrated data engineering expertise, including custom-built programs capable of processing in excess of 700 million records in under 30 minutes on a highly frequent, recurring basis.
Proven expertise working with CCWIS data attributes to predict child welfare outcomes, including data attribute selection, data cleanup, and statistical tuning.
Extensive knowledge of statistical algorithms, machine learning, and adaptive systems.
Prior history of designing and building machine learning algorithms from the ground up.
Experience evaluating technical trade-offs between algorithmic approaches based on collective errors, computational time, scalability, and outcomes.
Prior success in developing optimal non-rule-based decision-making systems where inputs are stochastic.
Demonstrated success in converting social processes and human decision-making into computational models that yield improved results.