Cloud & AI Engineer
Architecting cloud infrastructure and generative AI systems at Lincoln Financial Group. Outside of work, I build hands-on learning projects to expand my skill set across multi-agent AI, ML pipelines, and end-to-end cloud architecture.
2+
Years at LFG
4.0
GPA (MS + BS)
2
Personal Learning Builds
Experience
Lincoln Financial Group
Cloud & MLOps Software Engineer
- Developing and maintaining Lincoln's enterprise Dataiku DSS platform — engineering user provisioning, project environment configuration, and governance workflows for our team's data science operations
- Architecting Amazon Bedrock integration for my team within Lincoln's AWS environment — designing and configuring IAM roles, VPC endpoints, service quotas, and security guardrails to enable generative AI capabilities in production
- Building and maintaining AWS cloud infrastructure for my team — implementing landing zone configurations, IAM governance tooling, and automated service health monitoring across enterprise environments
- Developing CI/CD pipelines and automation tooling for cloud resource management — scripting AWS provisioning, access reviews, and infrastructure lifecycle workflows
Lincoln Financial Group
Cloud & Software Engineering Intern
- Built CI/CD pipelines with Python and Ansible for AWS service automation, increasing availability by 4%
- Automated cloud resource monitoring via GitLab CI, reducing monthly costs by $3,000+
Projects
Hands-on learning project exploring multi-agent AI systems — a desktop tool I built to deepen my understanding of coding agent orchestration, MCP, and parallel git worktree workflows.
Parallel Agents
Multiple coding agents running in isolated git worktrees with human-in-the-loop approval gates
Multi-Provider LLM
Supports Claude, Codex, and local models via Model Context Protocol (MCP)
Persistent Memory
CTO Agent with long-term memory and Linear integration for autonomous issue triage
Versic
Audio ML & Full-Stack Cloud Build
Self-directed learning project to build an end-to-end cloud system — full-stack web, Electron desktop, native macOS Finder integration, and a serverless ML pipeline for audio analysis.
Audio ML Pipeline
View full diagram ↗Step Functions state machine · Modal T4 GPU · ~$0.02 per track
Learn about CLAP (Contrastive Language-Audio Pretraining) ↗Campus Companion
RAG-Powered University Chatbot
AI chatbot using Retrieval Augmented Generation with LlamaIndex to help students access campus resources.