Data Engineer, AI

Job description

**Who we are:** At Focused, we move quickly to deliver quality software that achieves client outcomes and meets their customer's needs. We strategically partner with our clients to leverage our expertise in design and software, while our clients bring their own domain expertise. We work with a variety of clients from different industries, collaborating as we get new products to market, modernizing legacy systems, or helping teams learn the skills they need to be successful. **Our values:** - *Listen first* • We are experts in product practices but lifelong learners in the domain of our customers. We research, collaborate, and understand. - *Learn why* • We ask questions and talk to users to understand problem spaces, objectives, and goals, which allows us to deeply invest and drive towards the outcomes of our clients. - *Love your craft* • We love diving into a variety of domains and solving problems. We take pride in delivering value, in communicating progress, and guiding our clients to success. We're looking for a Data Engineer to build the data foundation behind an enterprise AI platform for a global enterprise client. Agents and LLM applications are only as good as the data they can reach, and you'll own getting it there: clean, governed, and ready for retrieval. Most of your work will be in Databricks, with a strong lean toward AI use cases. **Key Responsibilities:** **Data Pipelines & Platform** - Design and build batch and streaming pipelines in Databricks (Spark, Delta Lake, Workflows) - Model data in a lakehouse architecture that serves both analytics and AI workloads - Implement governance and access controls with Unity Catalog - Monitor data quality and pipeline reliability **Data for AI** - Build ingestion and chunking pipelines for unstructured data (documents, PDFs, knowledge bases) that feed RAG systems - Generate, store, and refresh embeddings; operate vector search (Databricks Vector Search or similar) - Build datasets for LLM evaluation and help teams measure retrieval quality - Partner with AI and platform engineers so agents get the right data with the right permissions **Cloud & Engineering Practices** - Deploy data infrastructure on Azure and/or GCP using IaC - Bring software engineering habits to data work: version control, testing, CI/CD **Required Qualifications:** - 5+ years in data engineering - Strong hands-on experience with Databricks, Spark, and Delta Lake - Proficiency in Python and SQL - Experience building production data pipelines in a cloud environment (Azure or GCP preferred) - Experience with data modeling and data quality practices **Preferred Qualifications (Exceptional Candidates):** - Experience building data pipelines for RAG, embeddings, or vector search - Experience with Unity Catalog and Mosaic AI - Experience with streaming (Structured Streaming, Kafka, Event Hubs) - Consulting or client-facing experience **What Sets Exceptional Candidates Apart:** - You've improved an AI system's answers by fixing the data underneath it - You've handled messy unstructured data at scale - Databricks certifications or open-source contributions **What to know before you apply:** - This role will require being in the Chicago office 3 days per week and up to 20% travel within the United States. - Focused is unable to sponsor or take over sponsorship of the employment Visa process at this time. - The Chicago base salary range for this role is $145,000 - $175,000.