Implementing AI data pipelines that bring together structured, semi-structured and unstructured data to support AI and Agentic solutions.
Requirements
- 8+ years of data engineering experience including Data solutions, SQL and NoSQL, Snowflake, ETL/ELT tools, CICD, Bigdata, Cloud Technologies (AWS/Google/AZURE), Python/Spark, Datamesh, Datalake or Data Fabric.
- 3+ years of AI/ML experience, with 1+ years of data engineering experience focused on supporting Generative AI technologies.
- Strong hands-on experience implementing production ready enterprise grade AI data solutions.
- Experience with prompt engineering techniques for large language models.
- Experience in implementing Retrieval-Augmented Generation (RAG) pipelines, integrating retrieval mechanisms with language models.
- Experience of vector databases and graph databases, including implementation and optimization.
- Proficiency in implementing scalable AI driven data systems supporting agentic solution (AWS Lambda, S3, EC2, Langchain, Langgraph).
Responsibilities
- AI Data Engineering lead responsible for Implementing AI data pipelines that bring together structured, semi-structured and unstructured data to support AI and Agentic solutions. This Includes pre-processing with extraction, chunking, embedding and grounding strategies to get the data ready.
- Develop AI-driven systems to improve data capabilities, ensuring compliance with industry best practices.
- Implement efficient Retrieval-Augmented Generation (RAG) architectures and integrate with enterprise data infrastructure.
- Design, build and maintain scalable and robust real-time data streaming pipelines using technologies such as Apache Kafka, AWS Kinesis, Spark streaming, or similar.
- Develop data domains and data products for various consumption archetypes including Reporting, Data Science, AI/ML, Analytics etc.
- Ensure the reliability, availability, and scalability of data pipelines and systems through effective monitoring, alerting, and incident management.
- Develop graph database solution for complex data relationships supporting AI systems.
Other
- This role will have a Hybrid work schedule, with the expectation of working in an office location (Hartford, CT; Chicago, IL; Columbus, OH; and Charlotte, NC) 3 days a week (Tuesday through Thursday).
- Collaborate with cross-functional teams to integrate solutions into operational processes and systems supporting various functions.
- Stay up to date with industry advancements in AI and apply modern technologies and methodologies to our systems.
- Collaborate closely with DevOps and infrastructure teams to ensure seamless deployment, operation, and maintenance of data systems.
- Mentor junior team members and engage in communities of practice to deliver high-quality data and AI solutions while promoting best practices, standards, and adoption of reusable patterns.
