· Design, develop, and maintain scalable data pipelines for ingesting, processing, and transforming large volumes of structured and unstructured data.
· Implement efficient data processing workflows to support the training and evaluation of solutions using large language models, ensuring reliability, scalability, and performance.
· Addressing issues related to data quality, pipeline failures, or resource contention, ensuring minimal disruption to systems.
· Integrate Large Language Model into data pipeline for natural language processing tasks.
· Working with Snowflake ecosystem
· Deploying, scaling, and monitoring AI solutions on cloud platforms like Snowflake, Azure, AWS, GCP
· Communicating technical and non-technical stakeholders and collaborate with cross-functional teams.
· Cloud cost management and best practices to optimize cloud resource usage and minimize costs.
Data Engineer – Preferred Qualifications:
- Experience working within the Azure ecosystem, including Azure AI Search, Azure Storage Blob, Azure Postgres and understanding how to leverage them for data processing, storage, and analytics tasks.
- Experience with techniques such as data normalization, feature engineering, and data augmentation.
- Ability to preprocess and clean large datasets efficiently using Azure Tools /Python and other data manipulation tools.
- Expertise in working with healthcare data standards (ex. HIPAA and FHIR), sensitive data and data masking techniques to mask personally identifiable information (PII) and protected health information (PHI) is essential.
- In-depth knowledge of search algorithms, indexing techniques, and retrieval models for effective information retrieval tasks. Familiarity with search platforms like Elasticsearch or Azure AI Search is a must.
- Familiarity with chunking techniques and working with vectors and vector databases like Pinecone.
- Experience working within the snowflake ecosystem.
- Ability to design, develop, and maintain scalable data pipelines for ingesting, processing, and transforming large volumes of structured and unstructured data.
- Experience with implementing best practices for data storage, retrieval, and access control to ensure data integrity, security, and compliance with regulatory requirements.
- Be able to implement efficient data processing workflows to support the training and evaluation of solutions using large language models, ensuring reliability, scalability, and performance.
- Ability to proactively identify and address issues related to data quality, pipeline failures, or resource contention, ensuring minimal disruption to systems.
- Experience with large language model frameworks, such as Langchain and know how to integrate them into data pipelines for natural language processing tasks.