AI Framework Engineer

Intel Intel · Semiconductors · Gdansk, Poland

Develop and enhance serving capabilities for generative AI and traditional ML models, focusing on performance optimization, scalability, and integration with AI applications and agentic solutions.

What you'd actually do

  1. Develop and enhance the serving component supporting generative AI use cases as well as classical AI models
  2. Drive performance optimization and troubleshooting, with a strong focus on high-concurrency and scalable workloads
  3. Integrate serving solutions with high-level AI applications and frameworks
  4. Design, build, and leverage agentic solutions to improve automation and system intelligence
  5. Implement generative algorithms to support emerging AI use cases

Skills

Required

  • C++
  • Python
  • AI/ML systems engineering
  • model deployment
  • model serving architectures
  • performance optimization
  • distributed systems
  • high-load environments
  • production-ready applications
  • reliability
  • scalability
  • quality

Nice to have

  • generative models
  • state-of-the-art algorithms in the GenAI space
  • agentic solutions

What the JD emphasized

  • Strong experience in AI/ML systems engineering and model serving
  • Proven ability to optimize performance in distributed or high-load environments
  • Familiarity with modern AI frameworks and agentic architectures
  • Solid understanding of generative AI concepts and algorithms

Other signals

  • serving generative AI
  • performance optimization
  • scalable workloads
  • agentic solutions