AI Engineer • Backend Systems • Developer Tooling

Building reliable AI infrastructure, evaluation systems, and high-leverage internal tooling.

Portfolio • LinkedIn • Email • YouTube

I’m a Software Engineer focused on building observable, trustworthy, and scalable AI systems.

I currently work at a Fortune 500 financial institution, where I build tooling at the intersection of LLM systems, retrieval pipelines, data validation, and engineering infrastructure. My background in large-scale automation and reliability engineering has given me a strong skillset in measurement, correctness, and production confidence, as well as a deep understanding of distributed & applied AI systems.

I’m especially interested in:

• RAG systems and evaluation pipelines
• AI infrastructure, observability, and governance
• Developer tooling and workflow automation
• Agentic systems and MCP-style orchestration
• High-leverage backend engineering problems

Anything worth doing is worth doing all the way.
Don’t mistake a plateau for the peak.

• RAG evaluation and validation tooling for model-driven systems
• Internal analytics and monitoring workflows for AI quality and consistency
• Agentic QA and automation experiments using Playwright + Claude Code
• MCP-style integrations for safer, more capable AI workflows
• Personal engineering content around Claude Code, tooling, and systems thinking

November 2025 – Present

• Design and build evaluation tooling for retrieval-augmented and model-driven systems, with an emphasis on making AI behavior measurable, explainable, and production-ready.
• Develop RAG evaluation pipelines using metrics such as Precision@k, Recall@k, and MRR to better understand retrieval quality, ranking performance, and answer usefulness.
• Build internal analytics and validation tools with Python, Pandas, and Streamlit to surface trends in model quality, retrieval effectiveness, and system consistency.
• Contribute to drift detection and monitoring workflows that identify changes in retrieval behavior, response quality, and data integrity across enterprise AI systems.
• Create automated validation frameworks that cross-reference outputs across S3 artifacts, Salesforce data, internal services, and structured evaluation datasets to improve traceability and confidence.
• Explore agentic engineering patterns and MCP-enabled workflows for safely connecting models to internal tools, development pipelines, and evaluation systems.

October 2024 – November 2025

• Built and scaled UI and API automation infrastructure using Playwright, TypeScript, and Cucumber for enterprise applications with high reliability requirements.
• Designed supporting orchestration layers and backend workflows that made automation more deterministic, maintainable, and scalable.
• Developed CI/CD regression systems with GitLab CI, AWS Lambda, DynamoDB, and S3, improving pipeline reliability and reducing operational friction.
• Served as a technical owner for framework architecture, reliability improvements, and engineering standards around automation and validation.
• Conducted technical interviews and helped onboard engineers into shared tooling, framework usage, and quality-focused engineering practices.

AI Systems
RAG Evaluation Precision@k Recall@k MRR Drift Detection Model Validation

Backend & Infrastructure
AWS Event-Driven Systems Data Pipelines System Reliability Internal Tooling

Developer Tooling
Playwright FastAPI FastMCP Claude Code Automation Frameworks

Languages
Python TypeScript JavaScript C++ Java SQL

• Email: bamoses2001@gmail.com
• LinkedIn: https://www.linkedin.com/in/blaise-moses
• Portfolio: https://www.blaisemoses.com
• YouTube: https://www.youtube.com/@BlaiseM_Programming