On-Device ML Engineer

Edge Deployment

RemoteContract / Part-time3-4 months

About the Role

We are seeking an ML engineer experienced in deploying lightweight models in constrained runtime environments.

Responsibilities

  • ▪Design, train, and evaluate lightweight ML models
  • ▪Optimize models for low latency and minimal memory footprint
  • ▪Convert and deploy models for mobile runtime (e.g., TensorFlow Lite or similar)
  • ▪Collaborate with C++ and Android engineers on inference integration

Requirements

  • ▪Experience deploying ML models in production
  • ▪Familiarity with model quantization and optimization
  • ▪Strong experimental and metrics-driven mindset
  • ▪Practical approach focused on shipping working systems

Apply Now

Interested in this position? Send your application to careers@404-founders.com

To help us review applications efficiently, please make sure to include your rate expectations and a short description of relevant projects.