Deep Learning Engineer

Job Description

Job Title: Senior Deep Learning Engineer. Location: Remote - Warsaw, Poland, Germany, Switzerland, Netherlands, UK

You will collaborate with research scientists, software engineers, and hardware experts to enhance performance for AI applications across autonomous vehicles, robotics and video analytics.

Duties:

• Improve inference performance for Cosmos WFMs across diverse GPU platforms.
• Deploy optimized deep learning models for real-time applications;
• Profile workloads and remove performance bottlenecks in training and inference.
• Implement and tune inference optimization techniques such as quantization;
• Work with frameworks like TensorRT, TensorRT-LLM, vLLM, or SGLang to streamline inference efficiency.
• Collaborate with multi-disciplinary teams to integrate physical AI models into production environments.

Qualifications:

• Master’s or PhD in Computer Science, Electrical Engineering, or related field.
• At least five years of experience in deep learning model development and deployment.
• Proficient in Python and PyTorch for model training and experimentation;
• Strong understanding of GPU optimization techniques and performance tuning.
• Experience using inference optimization frameworks (TensorRT, vLLM, SGLang, or similar).
• Knowledge of Docker and Triton Inference Server for production deployment;
• CUDA programming experience is a strong advantage.
• Familiarity with diffusion models is preferred.

Benefits and Instructions:

• Full-time engineering position based in Warsaw, Poland, with additional location options.
• Competitive salary and comprehensive NVIDIA benefits package;
• Opportunity to work on cutting-edge AI systems that power physical intelligence across industries.
• Apply online through NVIDIA’s career portal and upload your resume in English.