Model Optimisation & Deployment

Skill id

ai.model-deploy

Area

Systems & Applications

Group

Edge AI

Roadmap importance

No roadmap colour (added by TESA)

Origin

Added by TESA

Status in the lesson library

Assessed by a lesson

See it on the skill roadmap

Lessons that develop this skill

Lesson	Course	Develops to
What edge AI is: the five-stage data lifecycle and where a model can run	Edge AI Developer: From Sensor to On-Device Model	L1 Aware
Training in Docker: one artifact, four targets	Edge AI Developer: From Sensor to On-Device Model	L1 Aware
Inside training: Keras, Conv1D, gradient descent, int8 and the confusion matrix	Edge AI Developer: From Sensor to On-Device Model	L2 Guided
Running the model on the web: LiteRT.js, int8 I/O and parity	Edge AI Developer: From Sensor to On-Device Model	L3 Independent
Hands-on: a web verdict that matches the PC, and the Cortex-A story	Edge AI Developer: From Sensor to On-Device Model	L3 Independent
Quantize and Vela: putting our model on the Ethos-U55	Edge AI Developer: From Sensor to On-Device Model	L3 Independent
Hands-on: comparing three targets, MCU, web and PC	Edge AI Developer: From Sensor to On-Device Model	L3 Independent
The edge AI stack: tri-core, ai_engine, the IPC model link and TFLite-Micro	Edge AI Developer: From Sensor to On-Device Model	L3 Independent
Adding your own model: three edits, a four-function contract and Vela	Edge AI Developer: From Sensor to On-Device Model	L3 Independent
Hands-on: make a new model appear in edge_ai.models()	Edge AI Developer: From Sensor to On-Device Model	L3 Independent

Lessons that assess this skill

Lesson	Level	Evidence
Hands-on: a web verdict that matches the PC, and the Cortex-A story	L2 Guided	practice/s13_web.py
Hands-on: comparing three targets, MCU, web and PC	L2 Guided	practice/s14_tflite_board.py

Roles that use this skill

Role	Minimum level	In this role
Edge AI Engineer	L3 Independent	Required (R)

Proficiency levels

• L1 Aware · Bloom: remember/understand
• L2 Guided · Bloom: apply (scaffolded)
• L3 Independent · Bloom: apply/analyse
• L4 Professional · Bloom: analyse/evaluate
• L5 Design & Lead · Bloom: evaluate/create

For Open Badges 3.0 and CASE alignment

UUID: 93f86e29-0a67-5ecd-acba-0fc4b5835cac

{
  "type": [
    "Alignment"
  ],
  "targetName": "Model Optimisation & Deployment",
  "targetUrl": "https://tesaiot.github.io/tesa-qualification-program/skills/ai.model-deploy/",
  "targetCode": "ai.model-deploy",
  "targetFramework": "TESA Embedded Systems Skill Map 0.1.0",
  "targetType": "CFItem"
}

Skill map data is licensed CC BY-SA 4.0, adapted from the Embedded Systems Engineering Roadmap by Meysam Parvizi