Machine Learning Engineer – Model Optimization

About the role

We are looking for experienced Machine Learning Engineers to optimize and deploy ML models on heterogeneous embedded platforms. You will bridge research models and production hardware, focusing on the trade‑offs between model quality and computational efficiency.

Key responsibilities

• Profile and analyze ML models to find computational, memory and data‑movement bottlenecks.
• Develop hardware‑aware model optimization methodologies and neural architecture search using real hardware measurements.
• Apply quantization, mixed‑precision inference, distillation and other compression techniques.
• Maintain export, benchmarking and deployment pipelines across PyTorch, ONNX and TensorRT.
• Evaluate deployment strategies and map models onto CPUs, GPUs and dedicated AI accelerators.

Required profile

• Strong understanding of deep neural network architectures and hands‑on experience with PyTorch.
• Proficiency in Python programming.
• Experience analyzing inference performance and applying model compression methods.
• Familiarity with deployment frameworks such as ONNX and TensorRT.
• Ability to work across research, embedded software and product teams.

Required skills

• Python
• PyTorch
• ONNX
• TensorRT
• C++ (modern)
• CUDA / OpenCL
• Git and standard software development practices

What we offer

• Competitive salary €75,000–€90,000 per year plus equity.
• Hybrid work model: three days onsite in Paris, the rest remote.
• Modern office in central Paris, commuter benefits and subsidized meal vouchers.
• Wellness Pass and other employee benefits.