Build AI-assisted operational software that turns ERP, inventory, procurement, market-research, and order data into actionable workflows for operators.

• ->Designed AI-driven ERP workflows spanning order management, inventory visibility, procurement planning, and operational decision support
• ->Built a self-suggesting procurement system that uses inventory and order signals to surface replenishment needs and purchasing recommendations
• ->Developed market-research tooling that structures product, competitor, and demand information into usable inputs for planning and purchasing decisions

Observed and mapped factory production, cutting, merchandising, and IE/planning handoffs; developed process-improvement proposals.

• ->Mapped production and cutting handoffs and proposed traceable departmental updates
• ->Identified manual follow-up and information bottlenecks; no verified improvement percentage
• ->Documented end-to-end production and cutting workflows to support standardization and continuous improvement

Started by solving a real coordination problem for my university batch, then kept expanding the system as users and workflows exposed deeper constraints.

• ->Built and deployed the first usable slice instead of waiting to finish learning
• ->Learned product, architecture, deployment, and support through real usage
• ->Established the habit of validating technical decisions against an actual workflow

Started working independently on software, workflow automation, and digital products before moving into a formal AI engineering role.

• ->Worked directly with clients to turn ambiguous business needs into scoped software and automation deliverables
• ->Built practical workflow and web-based tools for operational and business use cases
• ->Developed early experience in requirements discovery, delivery ownership, and iterative improvement

A Rust/PostgreSQL multi-tenant commerce platform with merchant administration, storefronts, and a partially completed operator control plane.

Source migrations implement fail-closed tenant policies; integration and release gates exist, but the latest available CI runs failed.

A Rust-based research instrument for hall-entry identity verification and security monitoring, deliberately constrained to observe-only behavior.

Rust event-delivery code, observe-only invariants, and security gates exist. Latest CI and GPU release qualification remain unresolved.

A Go and Next.js academic LMS/ERP foundation exploring Moodle-scale institutional workflows with explicit tenant boundaries and a modular backend.

JWT rejection tests, modular Go APIs, and SQL migrations exist; the latest visible CI run failed and the teaching core remains incomplete.

A class operating system that centralizes announcements, schedules, resources, and AI-supported student workflows for an active academic community.

Built for a university cohort; the reported 60+ student users are not independently verified analytics.