Entry AI Engineer, Mainframe System Z & LLM Acceleration

International Business Machines Corporation; Munster; On-site; EUR 42,000 - 56,000; Full time

Job summary

IBM Infrastructure is seeking an entry-level AI Engineer to join our System Z mainframe team. You will work across the full stack—from firmware interfaces up to application APIs—to deploy and optimise LLMs on IBM Z hardware used by banks, healthcare providers and government agencies.

You will learn by collaborating with senior engineers on profiling, debugging, monitoring, and performance improvements, gaining hands-on experience in enterprise-scale AI deployment.

Qualifications

• Strong Python programming fundamentals and experience in C/C++.
• Fundamentals of machine learning, neural networks and transformer-based models.
• Interest in AI inference, profiling and performance optimisation.
• Knowledge of computer architecture, memory hierarchies and I/O systems.
• Strong problem-solving, debugging and documentation abilities.
• Collaborative mindset and curiosity for learning from experienced engineers.

Responsibilities

• LLM Integration and Deployment on System Z: develop, profile and integrate LLMs on System Z using Spyre cards.
• Performance Profiling and Optimisation: profile workloads to measure latency, throughput, memory usage and power; identify and implement improvements.
• Failure Analysis and Debugging: investigate issues across the stack and document root causes and resolutions.
• Observability and Telemetry Infrastructure: build monitoring, instrumentation, dashboards and alerts for real-time and historical analysis.
• Cross-Stack Collaboration: work with hardware, firmware, system software, AI research and application teams; contribute to design discussions and docs.
• Learning and Growth: stay up-to-date with LLMs and hardware acceleration; take part in training and mentorship.

Skills

Python

C/C++

Linux

ML fundamentals

Neural networks

Transformer models

AI inference

Performance profiling

Debugging

Technical comms

Tools

PyTorch

TensorFlow

Hugging Face Transformers

Profiling tools

CUDA

GPU programming

Git

CI/CD

Docker

Kubernetes

Job description

IBM Infrastructure is seeking an entry-level AI Engineer to join our System Z mainframe team. You will work across the full stack—from firmware interfaces up to application APIs—to deploy and optimise LLMs on IBM Z hardware used by banks, healthcare providers and government agencies.

You will learn by collaborating with senior engineers on profiling, debugging, monitoring, and performance improvements, gaining hands-on experience in enterprise-scale AI deployment.