Daniel Cárdenas
I build practical AI systems: RAG pipelines, voice and document automation, Python APIs, and the embedded telemetry that makes edge ML useful in the real world.
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.
Flagship case studies spanning the device, backend, and AI stack.
Mobile-first FaceID attendance system for mini solar farm crews, with on-device recognition, liveness, GPS/project checks, offline queueing, and photo-backed publishing.
Smart-meter NILM work spanning STM32 acquisition, Python services, MQTT telemetry, web tooling, OTA safety, and field-device rollout.
Local-first RAG with pgvector HNSW, BGE-M3, multilingual evals.
I help teams turn messy documents, device telemetry, and business processes into maintainable AI systems with clear APIs, measurable quality, and deployable demos.