Embedded AI engineer

The role

You work at the core of our AI expertise: fine-tuning, distillation and quantization of models to make them deployable on constrained devices. You bridge the gap between research and production engineering.

Responsibilities

• 01Fine-tune and distill models for specialized tasks
• 02Quantize and optimize inference for embedded and edge deployment
• 03Design private, sovereign data pipelines
• 04Implement guardrails and evaluation metrics

Requirements

• 01Strong experience in machine learning and deep learning
• 02Proficiency in PyTorch or TensorFlow
• 03Knowledge of quantization techniques (GGUF, GPTQ, AWQ)
• 04Ability to work autonomously on applied research topics

Nice to have

• 01Experience with ONNX Runtime or TensorRT
• 02Familiarity with microcontroller deployment
• 03AI publications or contributions