Inference Engineer — Low-Latency AI Pipelines

H Company; Paris; Hybride; EUR 60 000 - 90 000; Plein temps

Avantages offerts par ce poste

Competitive salary

Opportunities for professional growth

Collaborative multicultural team

Résumé du poste

H Company is seeking a skilled AI Engineer to develop scalable inference pipelines in Paris. Candidates should possess a MS or PhD in Computer Science or Machine Learning, along with proficiency in Python, Rust, or C/C++. The role emphasizes collaboration with research teams and optimizing GPU performance for low-latency tasks. A competitive salary and opportunities for professional growth are offered. The position operates in a hybrid model requiring presence in the office three days a week.

Qualifications

• Proficient in one of the programming languages: Python, Rust or C/C++.
• Experience in GPU programming such as CUDA and Open AI Triton.
• Experience in model compression and quantization techniques.

Responsabilités

• Develop scalable, low-latency and cost effective inference pipelines.
• Optimize model performance: memory usage, throughput, and latency.
• Collaborate with H research teams on model architectures.

Connaissances

Programming in Python, Rust, or C/C++

GPU programming (CUDA, Open AI Triton)

Model compression and quantization techniques

Strong communication and presentation skills

Collaborative mindset

Formation

MS or PhD in Computer Science, Machine Learning

Outils

Pytorch

ONNX Runtime

CUDA

Description du poste

H Company is seeking a skilled AI Engineer to develop scalable inference pipelines in Paris. Candidates should possess a MS or PhD in Computer Science or Machine Learning, along with proficiency in Python, Rust, or C/C++. The role emphasizes collaboration with research teams and optimizing GPU performance for low-latency tasks. A competitive salary and opportunities for professional growth are offered. The position operates in a hybrid model requiring presence in the office three days a week.