Senior Data AI Engineer

Join CNA Insurance in Chicago as a Senior Data AI Engineer. This onsite role focuses on designing, building, and operating end-to-end AI and ML solutions that migrate CNA to a modern cloud data lakehouse. You will work across structured and unstructured data, unlocking analytical value through scalable pipelines, retrieval augmented generation architectures, vector databases, and knowledge graphs. As a senior individual contributor, you will influence data strategies and may guide others, contributing to AI readiness at scale.

Location: Chicago, IL (onsite). Salary range: USD 72,000 - 141,000 per year.

Responsibilities

• Design and implement AI capabilities that accelerate legacy-to-cloud migrations, prioritizing scalability, reliability, and governance compliance.
• Build scalable ingestion and transformation pipelines for both structured and unstructured data sources, applying OCR, NLP preprocessing, and document chunking optimized for large language model consumption.
• Apply modern lakehouse patterns on Google Cloud Platform (GCP) with governance, cataloging, and lineage tracking to ensure data is discoverable, auditable, and AI-ready at scale.
• Design and deploy vector databases, embedding pipelines, and knowledge graph structures that serve as the retrieval layer for RAG and AI applications.
• Productionize AI solutions and advanced analytics within a DevOps/MLOps environment, including automated testing, monitoring, and rollback capabilities.
• Foster innovation by proposing new ideas and selecting the right combination of tools and frameworks to convert business problems into analytics solutions.
• Research and implement process improvements to address complex technology gaps, building a strong understanding of enabling technologies.

Requirements

• Deep expertise building scalable ingestion and transformation pipelines across structured and unstructured data, with a proven track record migrating workloads to modern cloud platforms.
• Experience parsing and normalizing diverse content types—PDFs, emails, images, call transcripts—using OCR and NLP preprocessing (tokenization, entity extraction, summarization) and document chunking optimized for LLMs.
• Proven experience designing and implementing vector databases (Vertex AI Vector Search, Pinecone, pgvector), embedding pipelines, and knowledge graph structures for RAG and semantic search.
• Strong SQL and data analytics skills; experience building data marts and feature datasets for data science and ML applications.
• Strong Python coding skills; hands-on experience with BigQuery, Claude Code, RAG architectures, LLMs, ADK, and prompt engineering techniques.
• Expertise in building ML platforms and data pipelines at scale; familiarity with ML algorithms, deep learning, NLP, information retrieval, and data mining techniques.
• Experience with Google Cloud Platform services (Vertex AI, Dataflow, BigQuery, Cloud Run, Pub/Sub) and comfort with distributed computing frameworks (Apache Spark, Dataproc) for large-scale processing.
• Solid experience managing diverse data sources with preprocessing, cleansing, and data integrity verification to meet ML requirements.
• Demonstrated experience with machine learning, deep learning, NLP, information retrieval, or data mining—particularly applied to unstructured or semi-structured data.
• Hands-on experience with vector databases, embedding models (text-embedding-gecko, OpenAI Ada, Cohere), and end-to-end RAG pipeline design.
• Experience using Agile methods is preferred.
• Strong communication and interpersonal skills; ability to collaborate effectively in a highly matrixed environment.
• Preferred experience with the insurance industry, its products and services.
• Experience implementing big data processing technologies; Apache Spark is preferred.

Technologies

• Python
• SQL
• Java
• BigQuery
• Claude Code
• Vertex AI
• Vertex AI Vector Search
• Pinecone
• pgvector
• OpenAI Ada
• Cohere
• text-embedding-gecko
• Dataproc
• Apache Spark
• Dataflow
• Cloud Run
• Pub/Sub
• Google Cloud Platform
• ADK

Reporting relationship: Typically to a Director or above.