Edge AI Engineer: LLM Optimization & On-Device Agents

MCA Nederland; Eindhoven; Sur place; EUR 70 000 - 90 000; Plein temps

Résumé du poste

A leading AI solutions company in Eindhoven, Netherlands, seeks experienced professionals to optimize large language models for edge environments. Responsibilities include enhancing AI system performance and developing agentic capabilities for resource-constrained hardware. Candidates should have postgraduate education, with over 5 years in AI engineering, proficient in Python and C/C++, and a solid foundation in model optimization techniques. This position offers an innovative working environment in a dynamic team.

Qualifications

• 5+ years of experience in software or AI engineering.
• Strong experience with LLMs and performance optimization.
• Experience with model optimization techniques like quantization and pruning.
• Experience with AI deployment toolchains and inference engines.
• Strong programming skills in Python, C/C++, and Linux.

Responsabilités

• Optimize large language models and multimodal models for edge devices.
• Apply optimization techniques to improve model performance.
• Develop agentic AI capabilities and secure workflows.
• Deploy models using various inference engines.
• Translate research into production-ready implementations.

Connaissances

Experience with large language models (LLMs)

Model optimization techniques

Proficient in Python

Strong programming skills in C/C++

Knowledge of AI frameworks (e.g., TensorFlow, PyTorch)

Familiarity with AI deployment toolchains

Experience with embedded systems

Understanding of safety mechanisms

Strong communication skills

Formation

MSc, EngD, or PhD in Computer Science or AI

Outils

PyTorch

TensorFlow

CUDA

TensorRT

ONNX

TFLite

llama.cpp

Description du poste

A leading AI solutions company in Eindhoven, Netherlands, seeks experienced professionals to optimize large language models for edge environments. Responsibilities include enhancing AI system performance and developing agentic capabilities for resource-constrained hardware. Candidates should have postgraduate education, with over 5 years in AI engineering, proficient in Python and C/C++, and a solid foundation in model optimization techniques. This position offers an innovative working environment in a dynamic team.