AI Data & Database Engineer – Modernization & AI Infrastructure

WEXWEXUS•Remote, OH

About The Position

WEX is seeking a Senior AI Data & Database Engineer to modernize critical SQL Server systems and build the data infrastructure for AI applications and agents. This role involves database modernization, performance engineering, data pipelines, and AI-native retrieval infrastructure. The engineer will work on modernizing legacy database systems by extracting business logic, improving performance, and enabling event-driven architectures, as well as building AI-ready data capabilities including embedding pipelines, vector search, RAG infrastructure, and retrieval services. The position requires a proactive approach to solving complex data problems and leveraging AI as an engineering accelerator, utilizing tools like GitHub Copilot, Cursor, and Claude Code for analysis, migration, troubleshooting, and automation.

Requirements

Strong hands-on experience with SQL Server, T-SQL, stored procedures, query optimization, and execution plans.
Proven experience modernizing legacy database systems and decomposing complex database logic into maintainable application or service architectures.
Strong understanding of relational database design, indexing, transactions, data integrity, and performance engineering.
Experience building production-grade data pipelines and integrating data through APIs, events, and batch processes.
Experience with one or more modern data platforms such as PostgreSQL, Snowflake, MongoDB, or Cosmos DB.
Practical experience with vector databases, embeddings, semantic search, RAG, or AI data pipelines.
Understanding of event-driven architectures and patterns such as CDC and transactional outbox.
Experience with cloud platforms and infrastructure-as-code, preferably AWS/Azure and Terraform.
Strong software engineering fundamentals, including version control, automated testing, CI/CD, and code review practices.
Demonstrated ability to use AI coding assistants effectively and willingness to incorporate AI into day-to-day engineering work.

Nice To Haves

Experience building data infrastructure specifically for LLM or agentic applications.
Experience with vector databases such as Pinecone, Azure AI Search, OpenSearch, pgvector, or similar technologies.
Experience with Kafka or other event-streaming platforms.
Experience developing retrieval services or RAG evaluation frameworks.
Experience creating internal AI-powered developer tools or automation.
Experience working in large-scale, distributed, cloud-native environments.

Responsibilities

Analyze complex SQL Server stored procedures and identify embedded business logic, dependencies, and data access patterns.
Refactor stored procedures using established architectural patterns to simplify data access, improve maintainability, and enable business logic to move into services.
Design and execute database migrations while maintaining data integrity, availability, and backward compatibility.
Analyze execution plans, optimize queries, and design effective indexing strategies for high-volume workloads.
Implement event-driven database patterns including CDC, outbox patterns, and event publishing.
Build automated tests and validation processes for database changes, migrations, and refactored procedures.
Create structured, AI-consumable documentation including annotated schemas, procedures, dependencies, and system context.
Build embedding pipelines covering text extraction, preprocessing, chunking, embedding generation, and vector storage.
Implement and optimize vector databases, vector indexes, semantic search, and hybrid retrieval patterns.
Build synchronization pipelines that keep vector stores aligned with source systems.
Develop retrieval APIs and services consumed by AI applications and agents.
Implement evaluation and monitoring for RAG systems, including retrieval quality, latency, relevance, and data freshness.
Partner with AI/ML engineers to improve embedding strategies, retrieval quality, and overall AI data performance.
Design and implement reliable ETL/ELT pipelines across SQL Server, PostgreSQL, Snowflake, and cloud data services.
Build API-based ingestion, event streaming, and batch-processing workflows.
Implement data quality, validation, observability, and operational monitoring for data pipelines.
Develop infrastructure-as-code for database provisioning and configuration using Terraform and ARM/Bicep.
Support NoSQL data solutions including MongoDB and Cosmos DB, with a focus on data modeling and query performance.
Design data access patterns that support domain-driven architectures, including repositories, query services, and read models.
Use AI coding assistants daily to accelerate database analysis, code generation, debugging, testing, and documentation.
Develop prompts, scripts, and workflows that apply AI to database engineering and modernization challenges.
Contribute to AI-powered engineering tools such as stored procedure analyzers, schema documentation generators, and migration assistants.
Create structured context and artifacts that enable AI agents and coding tools to reason effectively about data systems.
Evaluate emerging AI tools and identify practical opportunities to improve engineering productivity.
Partner with application, platform, and AI/ML engineers to design scalable, reliable data solutions.
Participate in code and architecture reviews for database, data platform, and AI infrastructure changes.
Troubleshoot complex production data and performance issues and contribute to operational support as needed.
Document technical decisions, patterns, and solutions so knowledge is reusable across engineering teams.
Mentor engineers on database design, performance optimization, data engineering, and modern engineering practices.