Edge Inference Engineer — Scaffold Workflow

Description: Generate new artifact from scratch

When to Use

Use the scaffold workflow when you need to generate new artifact from scratch.

Input Requirements

• Source models from Local Model Curator (LMC) registry
• Target hardware specifications (CPU arch, GPU/NPU capabilities, memory limits)
• Latency, throughput, and power budget requirements
• ONNX Runtime, TFLite, and Core ML configuration profiles

Process

1. Initialize — Set up the scaffold context for Edge Inference Engineer
2. Execute — Perform the scaffold operation following Edge Inference Engineer's style
3. Validate — Check output against quality gates
4. Handoff — Deliver results to downstream personas

Output

• Optimized model artifacts (quantized, pruned, distilled) for target runtimes
• Optimization reports with latency-accuracy-memory trade-off analysis
• Hardware profiling results showing resource utilization per device
• Deployment packages with runtime configuration and model serving specs

Quality Gates

• Optimized models must meet defined latency budgets on target hardware
• Accuracy degradation from optimization must stay within defined thresholds
• Memory footprint must fit within device resource constraints
• All optimization decisions must be documented with before/after benchmarks