Data Science Engineer

September 16

Apply Now

Receive Emails with Similar Jobs

Zelis

WebsiteLinkedInAll Job Openings

healthcare payments • payment integrity • payment accuracy • healthcare bill review • electronic payments

1001 - 5000

💰 $20.1M Venture Round on 2020-01

Description

• Overseeing data functions such as ingestion of structured/unstructured data, transformation, standardization, and QA to build robust and automated data pipelines. • Document and maintain robust processes that move large amounts of complex data between multiple data storage systems, including text extracts, RDBMS, and parquet formats. • Develop and maintain data pipelines specifically for NLP and Generative AI models, ensuring data is properly preprocessed and transformed for model training and deployment, utilizing Snowflake for scalable data warehousing solutions where applicable. • Perform deep-dive analyses using SQL & Python, leveraging data science and big data tools to garner actionable insights and identify and clean complex data quality issues. • Collaborate with AI/ML teams to support the training, fine-tuning, and deployment of NLP and Generative AI models. • Implement and optimize NLP model pipelines using frameworks such as TensorFlow, PyTorch, or Hugging Face Transformers, integrating them with existing data infrastructures, including Snowflake for enhanced data management and accessibility. • Monitoring, reviewing, and analyzing inbound and outbound data. • Proactively identifying issues and trends through data analysis and manipulation. • Analyze and refine text data, including tokenization, embedding generation, and handling large-scale language models, to enhance NLP model performance, leveraging Snowflake’s capabilities for managing and processing large text datasets. • Presenting findings in reports and utilizing various visualization techniques and tools like Power BI and Python data visualization tools. • Communicating effectively with cross-functional teams. • Support the integration of NLP models into business applications, ensuring that they deliver actionable insights and meet performance benchmarks, with Snowflake serving as a core component for data storage and analytics. • Creating and maintaining code through GitHub repository for change control. • Supporting off-hours data processing and emergency requests.

Requirements

• Advanced Python skills, including popular data science libraries such as Pandas, Numpy, Matplotlib, or similar. • Experience with NLP libraries and frameworks such as SpaCy, NLTK, or Hugging Face Transformers. • Advanced SQL skills. • Experience with Snowflake for data warehousing, including integration with other data processing tools and platforms. • Experience with big data using Spark (PySpark, Scala) and knowledge of Spark Internals. • Experience working with Generative AI models, including training and fine-tuning language models like GPT. • Experience with AWS. • Bachelor’s degree (Statistics, Math, Computer Science, or related field) and a minimum of 2 to 5 years related experience and/or training; or equivalent combination of education and experience as a data engineer/analyst/scientist. • Strong health care data knowledge (medical claims data, clinical data, pharmacy data, and eligibility data) preferred. • Experience in deploying NLP models in production environments, particularly in industries such as healthcare or finance, utilizing Snowflake for scalable data solutions. • Experience with version control software (Git preferred), agile development experience, and knowledge of design patterns. • Experience working independently, contributing as a member of the team, and being results-driven. • Ability to communicate complex NLP and AI concepts to non-technical stakeholders in a clear and concise manner. • Strong presentation skills to explain and present advanced statistical methods using non-technical language to key business stakeholders.