Deep Learning Solutions Architect – Inference Optimization

This role is remote with options available in the UK, Poland, Spain, Switzerland, and Germany.

Responsibilities:

• Work directly with key customers to understand their technology and provide the best AI solutions.
• Perform in-depth analysis and optimization for GPU architecture systems.
• Collaborate with Engineering, Product, and Sales teams to develop suitable solutions.

Requirements:

• MS/PhD or equivalent experience in relevant fields.
• 5+ years of experience with Python/C++ and modern NLP.
• Strong communication and presentation skills in English.

Tech stack:

Tools such as TRT LLM, vLLM, SGLang, Megatron-LM, NeMo, DeepSpeed, TensorRT-LLM, and Triton Inference Server.