This job was posted by https://idahoworks.gov : For more information,please see: https://idahoworks.gov/jobs/2153919

　　Machine Learning Scientist II

　　Remote or Hybrid or On-site within OR, WA, ID or UT

　　Cambia Health Solutions is working to create a seamless andfrictionless health care experience for consumers nationwide. Thispresents a unique challenge and opportunity for innovative solutionsthat serve patients and providers and influence the healthcare system.Cambia\'s AI team builds, prototypes, and deploys data-driven models andalgorithms to production systems, delivering more equitable, effective,and affordable health care to our members.

　　We are seeking a talented and skilled Machine Learning Scientist II tojoin us and help advance our current and future work applying machinelearning, deep learning, and NLP to deliver better health care. Wecontribute broadly across Cambia, working on a wide range of challengingproblems, for instance:

　　Reducing our members\' claim costs using both supervised andunsupervised approaches.Speeding up prior authorizations and appeals using NLP to understandclinical notes.Personalizing member engagement to promote the health and well-beingof our members.Driving health equity across Cambia initiatives.And much more!As a Machine Learning Scientist II, you will play a vital role inunderstanding requirements, prototyping and building models, conductingexperiments, and driving innovative solutions. Your passion for machinelearning, deep learning, and NLP, coupled with your eagerness to learnand grow, will be instrumental in advancing Cambia\'s data-driveninitiatives.

　　Qualifications & Requirements:

　　Academic degree (master\'s or PhD preferred) in Data Science,Computer Science, Statistics, or a related field.

　　Machine learning: Strong mathematical foundation andunderstanding of the concepts underlying machine learning, deeplearning, NLP, statistical modeling, and data analysis. Familiaritywith common machine learning frameworks and libraries such asTensorFlow, PyTorch, scikit-learn, XGBoost, etc. Understanding ofstandard algorithms (e.g., search & sort) and data structures, andtheir analysis.

　　NLP: Expertise in NLP and experience using LLM and NLP librarieslike NLTK, spaCy, or Hugging Face transformers is a plus.

　　Model development and evaluation: Experience applying a varietyof ML techniques and approaches to solve problems. Strong foundationin model evaluation, including metric development and selection.

　　Familiarity with production systems: Basic understanding ofsoftware engineering principles and considerations for deploying MLmodels in production systems. Exposure to containerizationtechnologies (e.g., Docker, Kubernetes) and cloud platforms (e.g.,AWS, Azure, GCP) is helpful. Understanding of model monitoring andMLOps.

　　Data preprocessing and analysis: Understanding of how tostructure machine learning pipelines. Familiarity with datapreprocessing techniques and tools. Experience with SQL and/orpython data processing libraries (e.g., Pandas, NumPy).

　　Analytical mindset: Strong analytical thinking andproblem-solving abilities to contribute to data analysis andexperimental evaluations. Attention to detail and an eagerness tolearn from experimental results.

　　Communication and teamwork: Good communication skills tocollaborate effectively with cross-functional teams. Willingness tocollaborate and learn with team members.

　　Healthcare knowledge: Previous experience is beneficial but notrequired.

　　Responsibilities:

　　Model prototyping and development: Use machine learning, deeplearning, and NLP to prototype, develop, and refine models on top of ourML p atform, leveraging best practices and established frameworks.Implement algorithms and techniques to meet requirements and objectivesof specific business problems.

　　Experimentation and evaluation: Conduct experiments and evaluationsto assess the performance and effectiveness of different models andtechniques. Develop metrics that reflect the needs of the business fortheir use cases. Analyze experimental results, interpret findings, andprovide actionable recommendations.

　　Model deployment and productionization: Work with ML Engineers tooptimize and adapt models for real-time, scalable, and efficientperformance. Collaborate with engineering and infrastructure teams toensure seamless integration and deployment of models into productionsystems.

　　Requirement analysis and solution design: Collaborate withcross-functional teams to understand business requirements, define clearobjectives, and develop technical plans. Work with stakeholders toidentify opportunities where machine learning techniques can providevaluable insights and solutions.

　　Data preprocessing and feature engineering: Implement robust andreusable data preprocessing and feature engineering pipelines to extractmeaningf