---
title: "edge-embedded-ai-engineer"
description: "Reasons from tensor-arena budgets, full-int8 PTQ with representative calibration, and TFLM/CMSIS-NN or Vela/Ethos-U compile paths through ONNX Runtime QNN HTP and mobile delegates, treating train, serve preprocessing ske"
canonical: https://agentpluginsdirectory.com/plugins/edge-embedded-ai-engineer
last-updated: 2026-11-13
---

# edge-embedded-ai-engineer
Reasons from tensor-arena budgets, full-int8 PTQ with representative calibration, and TFLM/CMSIS-NN or Vela/Ethos-U compile paths through ONNX Runtime QNN HTP and mobile delegates, treating train, serve preprocessing skew, float thresholds on quantized outputs, and NPU operator fallback as first-class failure modes.
## Package we checked
The manifest we fetched is scientific-agents/edge-embedded-ai-engineer/plugin.json in K-Dense-AI/scientific-agents. The plugin root is the directory that holds that file. Its $schema is https://agent-plugins.org/schemas/1.0.0/plugin.schema.json. The manifest lists 1 skill (edge-embedded-ai-engineer) and no MCP servers.
- Slug: edge-embedded-ai-engineer
- Publisher: K-Dense
- Repository: https://github.com/K-Dense-AI/scientific-agents
- Manifest: scientific-agents/edge-embedded-ai-engineer/plugin.json
- Version: 1.0.0
- License: MIT
- Category (editorial): other
- Skills: 1 (edge-embedded-ai-engineer)
- MCP servers: 0
- Stars: 245
- Repository created: 2026-06-03
- Repository last pushed: 2026-10-02
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/edge-embedded-ai-engineer
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## Skills

- edge-embedded-ai-engineer: Think and work like an expert Edge / Embedded AI Engineer. Use when a task calls for Edge / Embedded AI Engineer judgment. Reasons from tensor-arena budgets, full-int8 PTQ with representative calibration, and TFLM/CMSIS-NN or Vela/Ethos-U compile paths through ONNX Runtime QNN HTP and mobile delega…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
