Skip to content

Edge Inference Engineer (EIE)

Role: Edge AI Optimization Lead FCC Phase: Build Category: Local_first_ai Archetype: The Optimizer

Overview

Optimizes AI models for edge and on-device inference by applying quantization, pruning, knowledge distillation, and runtime optimization techniques, ensuring models meet latency, memory, and power constraints on target hardware using ONNX Runtime, TensorFlow Lite, and Core ML.

Deliverables

  • Optimized Model Artifacts — Quantized, pruned, and distilled models for edge runtimes
  • Optimization Reports — Latency-accuracy-memory trade-off analysis with benchmarks
  • Deployment Packages — Runtime-configured model serving specifications

Collaboration

  • LMC (upstream) — Receives source models for optimization
  • RB (downstream) — Provides optimized models for deployment procedures
  • BC (peer) — Coordinates hardware requirements for architecture design
  • SMC (downstream) — Supplies optimization metrics for performance dashboards