Daniel Cárdenas
AI Automation · RAG · Edge ML
Portfolio
I'm Daniel Cárdenas, an AI automation engineer. This site is a curated set of production-oriented case studies: retrieval quality, document and voice automation, Python APIs, and the embedded telemetry that makes edge ML useful in the field.
18
Case studies
11
Open repos
3
Tracks
Work by track
Production-oriented case studies across RAG, LLM automation, OCR, field devices, and edge ML — each with architecture notes and measurable outcomes where possible.
Confidential finance automation project combining a React/Supabase prototype, Python analysis pipelines, Codex subagents, and executive Excel/PDF deliverables to compare contracts, bills, payroll, support documents, and operational exports.
Analyzed hundreds of client/account records across contract, billing, payroll, support-document, and operational sources
Mobile-first FaceID attendance system for mini solar farm crews, with on-device recognition, liveness, GPS/project checks, offline queueing, and photo-backed publishing.
Replaced fragile manual attendance/overtime records with biometric, photo-backed check-in/check-out events
Smart-meter NILM work spanning STM32 acquisition, Python services, MQTT telemetry, web tooling, OTA safety, and field-device rollout.
Real-time energy disaggregation at 10 Hz with sub-2-second latency
Local-first RAG with pgvector HNSW, BGE-M3, multilingual evals.
Latency p50 2.8s / p95 4.9s
Telegram bot that turns Spanish voice messages into confirmed inventory, sales, reservation, payment, and debt records.
Natural-language voice transactions parsed into structured JSON with Gemini
LLM-powered automation tools for clinical simulations and survey feedback, with Azure-hosted RAG and alignment workflows.
Azure-hosted LLM pipelines for clinical simulations and survey feedback analysis
RAG, voice/document workflows, evals, and Python services that can be tested and deployed.
STM32, telemetry, OTA safety, and ML pipelines that connect real devices to cloud systems.
Operational dashboards, reconciliation tools, and cloud-backed automations for business users.
I help teams turn messy documents, device telemetry, and business processes into maintainable AI systems with clear APIs, measurable quality, and deployable demos.