LLM Serving Engineer, Cloud AI Platform

Qualcomm; Cork; Hybrid; EUR 110,000 - 160,000; Full time

Benefits offered by this job

Salary and stock options

Performance bonus

Maternity/Paternity Leave

Employee stock purchase scheme

Pension matching

Education assistance

Relocation support

Insurance packages

Well-being memberships

Bike scheme

Employee clubs

Job summary

QT Technologies Ireland Limited is hiring LLM Serving Engineers to work on scalable inference platforms and ecosystem packages in Cork, Ireland. The role spans research, development, and deployment across teams, with emphasis on performance and collaboration.

Ideal candidates have strong Python, CUDA/Triton experience, and a solid foundation in CS fundamentals. This full-time position offers salary, stock, and growth opportunities in a rapidly evolving GenAI landscape.

Qualifications

• Bachelor's degree in Engineering, Information Systems, Computer Science, or related field, with 4+ years software engineering experience.
• Master's degree in Engineering, Information Systems, Computer Science, or related field, with 3+ years experience.
• PhD in Engineering, Information Systems, Computer Science, or related field with 2+ years experience.
• 2+ years of programming in C, C++, Java or Python.

Responsibilities

• Build a scalable LLM inference platform using advanced techniques and kernels.
• Contribute to LLM Serving packages (e.g. vLLM, Triton, LLM-d).
• Collaborate with customers and internal teams (compiler, firmware, platform).
• Explore advanced algorithms (attention, MoEs) to identify optimizations.
• Drive autoscaling, load balancing, and routing for efficient serving.
• Engage with open-source communities to evolve the framework.

Skills

Communication skills

Strong Python development

Deep learning fundamentals

MSL/ML optimization

Collaboration & teamwork

Education

Bachelor's degree in Engineering/CS/related field

Master's degree in Engineering/CS/related field

PhD in CS/Engineering/ML (advantageous)

Tools

C/C++/Java/Python

Job description

QT Technologies Ireland Limited is hiring LLM Serving Engineers to work on scalable inference platforms and ecosystem packages in Cork, Ireland. The role spans research, development, and deployment across teams, with emphasis on performance and collaboration.

Ideal candidates have strong Python, CUDA/Triton experience, and a solid foundation in CS fundamentals. This full-time position offers salary, stock, and growth opportunities in a rapidly evolving GenAI landscape.