Senior Software Developer, AI Data Engineer

Caseware is one of Canada's original Fintech companies, having led the global audit and accounting software industry for over 30 years, with more than 500,000 users across 130 countries and available in 16 different languages. While you might not have heard of us (yet) over 36,000 accounting and audit professionals list Caseware as a skill on their LinkedIn profiles! As a Senior Software Developer – AI Data Engineer, you will play a key role in defining, designing, and implementing the data architecture that powers Caseware’s AI platform. You will lead architecting and building scalable data ingestion, processing, storage, and retrieval systems across structured, unstructured, and multi-modal data sources, while establishing data models, governance standards, and platform capabilities that support vector search and graph-based knowledge representations. Working across AI, platform, and product teams, you will define and evolve reference architectures, data standards, guardrails, and best practices, while implementing data quality, lineage, traceability, metadata management, freshness monitoring, and alerting capabilities to ensure trusted, reliable, and audit-ready data products that enable AI innovation at scale across Caseware Cloud.     In this role, you will take ownership of complex, production-grade AI data workflows end-to-end, influence architectural direction through technical leadership and proof-of-concepts, and help ensure our Data platform is scalable, reliable, and measurable. You will collaborate closely with AI, platform, DevOps, and product teams to turn emerging AI patterns into durable platform capabilities that directly impact customers across Caseware’s cloud ecosystem.   📍 Location: This is a fully remote position located in Colombia.  Contact Maira Russo - Senior Talent Acquisition Partner   What you'll be doing:

• Design and implement reliable, scalable data ingestion and integration pipelines for structured, semi-structured, unstructured, and multi-modal data (e.g., databases, documents, APIs, events), ensuring data is AI-ready, governed, secure, and observable. 
• Build and scale retrieval infrastructure, including vector storage, embedding pipelines, hybrid search, and graph-based knowledge representations, while optimizing data modeling for retrieval quality. 
• Develop and operate agent memory systems and pipelines for AI system signals (tracing, feedback, evaluation, and usage data) to support observability and continuous improvement. 
• Apply data quality, validation, monitoring, and testing frameworks in production pipelines, ensuring governance, access control, lineage, and security standards are met, including safe handling of sensitive data in AI retrieval and generation workflows. 
• Monitor, troubleshoot, and optimize AI data pipelines and retrieval workflows for reliability, performance, and cost, with strong observability and resilient processing patterns. 
• Design and support evaluation workflows for AI systems, enabling offline testing, benchmarking, and continuous improvement of retrieval and agent performance over time. 
• Lead pragmatic platform evolution by defining clear contracts between AI services and data systems, reducing coupling, and improving developer experience. 

What you’ll bring: The Tech Stack You’ll Work With:

Backend & Platform: TypeScript, NestJS, Python 

Cloud & Infrastructure: AWS EKS, AWS Lambda, AWS Bedrock, AWS AgentCore 

Search & Retrieval: AWS OpenSearch Serverless, AWS S3 Vectors, AWS Knowledge Bases 

Document & Data Processing: AWS Textract, DynamoDB, S3 

AI Evaluation & Observability: LangFuse, LangSmith (or equivalent) 

AI-assisted development tools: GitHub Copilot

Developer Tooling: GitHub, GitHub Actions, Nx Monorepo 

Collaboration: Jira, Confluence, Microsoft Teams, Outlook 

Why this role exists What success looks like (first 6–12 months) Perks & Benefits