AI Framework Engineer

The Software Team at Intel develops client and data center software AI technologies, specialized NPU and GPU IPs, and collaborates with OSVs, ISVs, developers, partners, and OEMs. They deliver IP, SOCs, runtimes, and platforms to support Intel's CPU and GPU/accelerator roadmap, including integrated and discrete graphics.

• Strong knowledge of AI/ML systems engineering and model serving architectures
• Familiarity with generative models and state-of-the-art algorithms in the GenAI space
• Very good programming skills in C++ and Python
• Proven ability to optimize performance in distributed and high-load environments
• Experience in developing production-ready applications focusing on reliability, scalability, and quality
• Bachelor's degree in Computer Science or related fields
• Fluency in English

• Develop and enhance the serving component supporting generative AI and classical AI models
• Drive performance optimization and troubleshooting for high-concurrency, scalable workloads
• Integrate serving solutions with high-level AI applications and frameworks
• Design, build, and leverage agentic solutions to improve automation and system intelligence
• Implement generative algorithms to support emerging AI use cases

This role requires on-site presence in Gdansk, Poland. Intel is an equal opportunity employer and considers all qualified applicants without regard to protected characteristics under local laws.