ML Inference Systems Engineer — High-Performance Accelerator

Arago Inc.; Paris; On-site; EUR 110,000 - 170,000; Full time

Benefits offered by this job

Stock options

Health insurance

Pension contributions

Professional development

Job summary

Arago Inc. in Paris is seeking a senior ML inference engineer to optimize execution on a custom accelerator. You will work across kernels, model execution, and multi-device distribution to maximize performance and efficiency.

You will contribute to the software stack, with emphasis on CUDA/Triton-based kernels, operator fusion, and advanced inference-serving techniques; strong C++/Python skills and English proficiency are required.

Qualifications

• Strong experience in high-performance ML inference.
• Deep understanding of computer architecture and memory hierarchies.
• Experience developing and optimizing custom kernels (CUDA/Triton/ROCm).
• Experience with operator fusion, tiling, scheduling and data movement optimization.
• Experience with distributed model execution and parallelism.
• Hands-on with modern inference-serving systems (e.g., KV-cache, continuous batching).
• Strong C++ and Python skills; exposure to MLIR is a plus.
• English proficiency.

Responsibilities

• Analyze modern AI workloads to identify bottlenecks on Arago's accelerator.
• Develop and optimize custom kernels and execution strategies to maximize device utilization.
• Map models and operators across multiple Arago devices with efficient communication.
• Develop inference-serving techniques like continuous batching and KV caches.
• Build profiling and performance-analysis tools for kernels, models, and serving workloads.
• Collaborate with hardware, compiler, and runtime teams to influence future features.

Skills

ML inference

GPU/accelerator

Kernel optimization

Distributed execution

Inference-serving

C++

Python

English

Job description

Arago Inc. in Paris is seeking a senior ML inference engineer to optimize execution on a custom accelerator. You will work across kernels, model execution, and multi-device distribution to maximize performance and efficiency.

You will contribute to the software stack, with emphasis on CUDA/Triton-based kernels, operator fusion, and advanced inference-serving techniques; strong C++/Python skills and English proficiency are required.