Hybrid ML Engineer: Hardware-Aware Model Optimization

Aimlroles; Paris; Hybrid; EUR 75,000 - 90,000; Full time

Benefits offered by this job

Competitive salary

Hybrid work in Paris

Meal & wellness benefits

Job summary

Zendar seeks an experienced ML engineer to optimize and deploy machine learning models on heterogeneous embedded platforms. You will work where ML, compilers, runtimes, and architecture intersect, bridging researcher models with highly optimized production implementations.

The role emphasizes hardware-aware optimization, latency, throughput, and memory efficiency while preserving model quality. You will explore NAS, quantization, mixed-precision inference, and model compression for real-world

Qualifications

• Experience building and deploying ML models in production.
• Strong understanding of neural networks and hardware-aware optimization.
• Proficiency with Python and ML frameworks (e.g., PyTorch).

Responsibilities

• Profile and optimize ML models for latency, throughput, and memory.
• Develop hardware-aware model optimization and NAS methods.
• Map models across CPUs, GPUs, and AI accelerators.
• Develop export, benchmarking, and deployment pipelines (PyTorch, ONNX, TensorRT).
• Evaluate deployment strategies for heterogeneous hardware.

Skills

Python

ML algorithms

Profiling

Embedded systems

Tools

PyTorch

ONNX

TensorRT

CUDA

C++

Job description

Zendar seeks an experienced ML engineer to optimize and deploy machine learning models on heterogeneous embedded platforms. You will work where ML, compilers, runtimes, and architecture intersect, bridging researcher models with highly optimized production implementations.

The role emphasizes hardware-aware optimization, latency, throughput, and memory efficiency while preserving model quality. You will explore NAS, quantization, mixed-precision inference, and model compression for real-world